CN105405178B - driving recorder and operation method thereof - Google Patents

Abstract

A driving recorder and an operating method thereof. The driving recorder comprises a camera module, a database, a first image processing circuit and a second image processing circuit. The camera module is configured to capture a scene and output an original image. The first image processing circuit generates a first image based on part or all of the original image, and records the first image in the database. The second image processing circuit generates a second image based on part or all of the original image, and records the second image in the database. The viewing angle of the second image is different from that of the first image.

Description

Driving recorder and its operation method

technical field

The invention relates to an imaging device, and in particular to a driving recorder and an operating method thereof.

Background technique

Known driving recorders generally only record images from a single viewing angle. To record images from different angles of view, multiple camera modules (multiple sets of lenses and multiple image sensors) need to be configured in the driving recorder. For example, if it is desired to record a far-angle image frame and a close-angle image frame at the same time, it is necessary to configure a telephoto camera module and a wide-angle camera module in the driving recorder. The telephoto camera module has a set of telephoto lenses (Tele Lens) and an image sensor, which can be used to capture telephoto images (Tele image). The wide-angle camera module has a set of wide-angle lenses (Wide Lens) and another image sensor, which can be used to capture wide-angle images (Wide image). In any case, this design requires two sets of lenses and two image sensors, thus increasing the cost.

Contents of the invention

The invention provides a driving recorder and an operation method thereof, which can use a single lens to capture multiple image frames with different viewing angles.

The driving recorder in the embodiment of the present invention includes a camera module, a database, a first image processing circuit and a second image processing circuit. The camera module is configured to shoot scenes and output original image frames. The first image processing circuit is coupled to the camera module to receive the original image frame. The first image processing circuit generates a first image frame according to part or all of the original image frame, and records the first image frame in the database. The second image processing circuit is coupled to the camera module to receive the original image frame. The second image processing circuit generates a second image frame according to part or all of the original image frame, and records the second image frame in the database. Wherein, the viewing angle of the second image frame is different from the viewing angle of the first image frame.

In an embodiment of the present invention, the first image processing circuit and the second image processing circuit respectively adjust the resolution of the first image frame and the resolution of the second image frame, so that the resolution of the first image frame The resolution and the resolution of the second image frame are smaller than the resolution of the original image frame, so that the bandwidth resource provided by the database can meet the bandwidth requirement of recording the first image frame and the second image frame in the database.

In an embodiment of the present invention, the above-mentioned original image frame is a wide-angle image.

In an embodiment of the present invention, the above-mentioned first image processing circuit includes a first image extraction circuit and a first image scaling circuit. The input end of the first image extraction circuit is coupled to the camera module to receive the original image frame. The first image extraction circuit extracts a first sub-picture from the original picture. The input end of the first image scaling circuit is coupled to the output end of the first image extraction circuit. The first image scaling circuit adjusts the resolution of the first sub-frame to obtain the first image frame.

In an embodiment of the present invention, the above-mentioned first image processing circuit performs image recognition to find an object from the original image frame, and extracts a first sub-frame containing the object from the original image frame.

In an embodiment of the present invention, the aforementioned object may be a vehicle, a license plate, or a human face or other interesting characteristic images.

In an embodiment of the present invention, the above-mentioned second image processing circuit includes a second image extraction circuit and a second image scaling circuit. The input end of the second image extraction circuit is coupled to the camera module to receive the original image frame. The second image extraction circuit extracts a second sub-picture from the original picture. The input end of the second image scaling circuit is coupled to the output end of the second image extraction circuit. The second image scaling circuit adjusts the resolution of the second sub-frame to obtain the second image frame.

In an embodiment of the present invention, the above-mentioned first image processing circuit generates the first image frame according to all the original image frames. The first image processing circuit performs image recognition to find out the position of an object from the original image frame, and provides the position of the object to the second image processing circuit. The second image processing circuit extracts a second sub-frame containing the object from the original image frame as the second image frame according to the position of the object provided by the first image processing circuit.

In an embodiment of the present invention, the above driving recorder further includes a third image processing circuit. The third image processing circuit is coupled to the camera module to receive the original image frame. The third image processing circuit generates a third image frame according to part or all of the original image frame, and records the third image frame in the database. Wherein, the viewing angle of the third image frame is different from the viewing angle of the first image frame and the viewing angle of the second image frame.

The operation method of the driving recorder described in the embodiment of the present invention includes: taking pictures of the scenery by the camera module and generating the original image frame; generating the first image frame according to part or all of the original image frame by the first image processing circuit, and recording the first image frame in the database; and generating a second image frame according to part or all of the original image frame by the second image processing circuit, and recording the second image frame in the database. Wherein, the viewing angle of the second image frame is different from the viewing angle of the first image frame.

In an embodiment of the present invention, the step of generating the first image frame includes: extracting a first sub-frame from the original image frame; and adjusting the resolution of the first sub-frame to obtain the first image frame.

In an embodiment of the present invention, the above-mentioned step of generating the first image frame includes: performing image recognition to find an object from the original image frame; and extracting the first image containing the object from the original image frame. sprite.

In an embodiment of the present invention, the step of generating the second image frame includes: extracting a second sub-frame from the original image frame; and adjusting the resolution of the second sub-frame to obtain the second image frame.

In an embodiment of the present invention, the above-mentioned step of generating the first image frame includes: generating the first image frame according to the entire original image frame; and performing image recognition to find an object from the original image frame position, and provide the position of the object to the second image processing circuit. The above-mentioned step of generating the second image frame includes: extracting a second sub-frame containing the object from the original image frame as the second image frame according to the position of the object provided by the first image processing circuit.

In an embodiment of the present invention, the above operation method further includes: generating a third image frame by the third image processing circuit according to part or all of the original image frame, and recording the third image frame in the database. Wherein, the viewing angle of the third image frame is different from the viewing angle of the first image frame and the viewing angle of the second image frame.

Based on the above, the driving recorder and its operating method according to the embodiments of the present invention can provide the original image frames generated by the same camera module to different image processing circuits at the same time. Each of these different image processing circuits extracts and generates different image frames from the original image frame with different viewing angles. Therefore, the driving recorder and its operating method can use a single lens to capture multiple image frames with different viewing angles.

In order to make the above-mentioned features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail with reference to the accompanying drawings.

Description of drawings

FIG. 1 is a schematic circuit block diagram illustrating a driving recorder according to an embodiment of the present invention.

FIG. 2 is a schematic flowchart illustrating an operation method of a driving recorder according to an embodiment of the present invention.

FIG. 3 is a diagram illustrating an example of an image frame captured by the driving recorder shown in FIG. 1 according to an embodiment of the present invention.

FIG. 4 is a schematic circuit block diagram illustrating a driving recorder according to another embodiment of the present invention.

【Symbol Description】

100: driving recorder

110: camera module

111: Original image screen

120: Image processing circuit

120_1: the first image processing circuit

120_2: Second image processing circuit

120_3: The third image processing circuit

130: database

140_1: First image frame

140_2: Second image screen

140_3: Third image screen

310: license plate

320: Second sub-picture

400: driving recorder

421: The first image extraction circuit

422: The first image scaling circuit

423: Second image extraction circuit

424: Second image scaling circuit

S210～S250: steps

Detailed ways

The term "coupled" as used throughout the specification of this application (including the claims) may refer to any direct or indirect means of connection. For example, if it is described in the text that a first device is coupled to a second device, it should be interpreted that the first device can be directly connected to the second device, or the first device can be connected through other devices or some kind of connection means. indirectly connected to the second device. In addition, wherever possible, elements/components/steps using the same reference numerals in the drawings and embodiments represent the same or similar parts. Elements/components/steps using the same symbols or using the same terms in different embodiments can refer to related descriptions.

FIG. 1 is a schematic circuit block diagram illustrating a driving recorder 100 according to an embodiment of the present invention. The driving recorder 100 includes a camera module 110 , a plurality of image processing circuits 120 and a database 130 . In the embodiment shown in FIG. 1 , the image processing circuit 120 includes a first image processing circuit 120_1 , a second image processing circuit 120_2 and a third image processing circuit 120_3 . In some embodiments, the first image processing circuit 120_1 , the second image processing circuit 120_2 and the third image processing circuit 120_3 may be integrated into the same integrated circuit. In other embodiments, the first image processing circuit 120_1 , the second image processing circuit 120_2 and/or the third image processing circuit 120_3 may be implemented as different integrated circuits. In any case, the number of image processing circuits 120 can be determined according to design requirements. For example, in some embodiments, there are two image processing circuits 120 . In other embodiments, the number of image processing circuits 120 is four or more.

The camera module 110 can capture a scene and output an original image frame 111 . The first image processing circuit 120_1 is coupled to the camera module 110 to receive the original image frame 111 . The first image processing circuit 120_1 can generate the first image frame 140_1 according to part or all of the original image frame 111 , and record the first image frame 140_1 in the database 130 . The second image processing circuit 120_2 is coupled to the camera module 110 to receive the original image frame 111 . The second image processing circuit 120_2 can generate the second image frame 140_2 according to part or all of the original image frame 111, and record the second image frame 140_2 in the database 130, wherein the viewing angle of the second image frame 140_2 is different from that of the first image frame 140_1 viewing angle. The third image processing circuit 120_3 is coupled to the camera module 110 to receive the original image frame 111 . The third image processing circuit 120_3 can generate the third image frame 140_3 according to part or all of the original image frame 111, and record the third image frame 140_3 in the database 130, wherein the angle of view of the third image frame 140_3 is different from that of the first image frame The viewing angle of 140_1 and the viewing angle of the second image frame 140_2.

In some embodiments, the image processing circuits 120_1 , 120_2 and/or 120_3 may have an image scaling function to adjust the resolution of the image frames 140_1 , 140_2 and/or 140_3 . Therefore, the resolution of the original image frame 111 may be smaller than the resolution of the image frames 140_1 , 140_2 and/or 140_3 .

In some other embodiments, based on design requirements or other considerations, the image processing circuits 120_1, 120_2 and/or 120_3 may have an image cropping/extracting function, so as to crop/extract part of the sub-picture from the original image picture 111 as the image picture 140_1, 140_2 and/or 140_3. Therefore, the resolution of the original image frame 111 may be greater than the resolution of the image frames 140_1 , 140_2 and/or 140_3 .

In other embodiments, the original image frame 111 may be a wide-angle image. The image processing circuits 120_1 , 120_2 and 120_3 can crop/extract different parts from the original image frame 111 as the first sub-frame, the second sub-frame and the third sub-frame respectively. The image processing circuits 120_1 , 120_2 and 120_3 can adjust the resolutions of the first sub-picture, the second sub-picture and the third sub-picture to obtain the image pictures 140_1 , 140_2 and 140_3 respectively. For example, but not limited thereto, the resolutions of the image frames 140_1 , 140_2 and 140_3 may be high-definition (HD), full-high-definition (Full-HD) or other resolutions.

For example, when the image processing circuits 120_1 , 120_2 and 120_3 (or more image processing circuits) access the database 130 through the data bus, the bandwidth resources that the database 130 and the data bus can provide are limited. On the other hand, the storage space that the database 130 can provide is also limited. In order to allow these image processing circuits to effectively share the bandwidth resources and/or storage space provided by the database 130, the image processing circuits 120_1, 120_2, and 120_3 can respectively cut/extract different parts of the original image frame 111 to obtain the image frames 140_1, 140_2 with 140_3. The image processing circuits 120_1, 120_2, and 120_3 can respectively adjust the resolution of the image frame 140_1, the resolution of the image frame 140_2, and the resolution of the image frame 140_3, so that the resolution of the image frames 140_1, 140_2, and 140_3 is smaller than that of the original image frame 111. resolution. Since the resolutions of the image frames 140_1 , 140_2 , and 140_3 can be lowered, the bandwidth resources provided by the database 130 must meet the bandwidth requirements for recording the image frames 140_1 , 140_2 , and 140_3 in the database 130 . Therefore, the image processing circuits 120_1 , 120_2 and 120_3 can effectively share the bandwidth resources and/or storage space provided by the database 130 , and thus can store the image frames 140_1 , 140_2 and 140_3 in the database 130 in real time.

For the convenience of description, the image processing circuits 120_1 , 120_2 and the image frames 140_1 , 140_2 will be taken as examples below. Other image processing circuits (such as the third image processing circuit 120_3) can be deduced by referring to the relevant descriptions of the image processing circuit 120_1 or 120_2, and other image frames (such as the third image frame 140_3) can refer to the description of the image frame 140_1 or 140_2 Related instructions and so on.

FIG. 2 is a schematic flowchart illustrating an operation method of a driving recorder according to an embodiment of the present invention. 1 and 2, the camera module 110 captures the scene in step S210 and generates the original image frame 111 for the first image processing circuit 120_1, the second image processing circuit 120_2, the third image processing circuit 120_3 and other image processing circuits.

The first image processing circuit 120_1 generates a first image frame 140_1 according to part or all of the original image frame 111 (step S220 ), and records the first image frame 140_1 in the database 130 (step S230 ). The resolution of the first image frame 140_1 may be different (or the same) as that of the original image frame 111 . In some embodiments, the first image processing circuit 120_1 may extract all frames of the original image frame 111 as the first image frame 140_1 . In some other embodiments, the first image processing circuit 120_1 may extract a part of the original image frame 111 as the first sub-frame in step S220, and adjust the resolution of the first sub-frame to obtain the first image frame 140_1.

The second image processing circuit 120_2 generates a second image frame 140_2 according to part or all of the original image frame 111 (step S240 ), and records the second image frame 140_2 in the database 130 (step S250 ). The resolution of the second image frame 140_2 may be different (or the same) as that of the original image frame 111 . In some embodiments, the second image processing circuit 120_2 may extract all frames of the original image frame 111 as the second image frame 140_2 . In some other embodiments, the second image processing circuit 120_2 may extract a part of the original image frame 111 as the second sub-frame in step S240, and adjust the resolution of the second sub-frame to obtain the second image frame 140_2. Since the image processing circuits 120_1 and 120_2 can respectively crop/extract different partial frames from the same original image frame 111 , the viewing angle of the second image frame 140_2 can be different from that of the first image frame 140_1 .

In some embodiments, the first image processing circuit 120_1 may perform image recognition in step S220 to find an object (such as a vehicle, license plate, human face or other interesting characteristic images or objects) from the original image frame 111, And extract the first sub-frame containing the object from the original image frame 111 . The first image processing circuit 120_1 can adjust the resolution of the first sub-frame to obtain the first image frame 140_1 . For example, the first image processing circuit 120_1 can perform image recognition to find out the license plate position of the vehicle from the original image frame 111 . Next, the first image processing circuit 120_1 may extract a part of the frame containing the license plate from the original image frame 111 as the first sub-frame. The first image processing circuit 120_1 can adjust the resolution of the first sub-frame to obtain the first image frame 140_1 . That is to say, the first image processing circuit 120_1 can enlarge a part of the license plate in the original image frame 111 to form the first image frame 140_1 .

In some other embodiments, the first image processing circuit 120_1 may generate the first image frame 140_1 according to all frames of the original image frame 111 in step S220. For example, the first image processing circuit 120_1 can extract all the frames of the original image frame 111 and adjust the resolution of the extracted frames as the first image frame 140_1 . On the other hand, the first image processing circuit 120_1 may perform image recognition in step S220 to find out the position of an object (such as a vehicle, a license plate, a human face or other interesting characteristic images or objects) from the original image frame 111, And provide the position of the object to the second image processing circuit 120_2. According to the position of the object provided by the first image processing circuit 120_1 , the second image processing circuit 120_2 can extract the second sub-frame containing the object from the original image frame 111 as the second image frame 140_2 in step S240 .

For example, FIG. 3 is a diagram illustrating an example of an image frame captured by the driving recorder 100 shown in FIG. 1 according to an embodiment of the present invention. The camera module 110 captures the scene in step S210 and generates the original image frame 111 for the first image processing circuit 120_1 and the second image processing circuit 120_2 . The original image frame 111 may be any resolution image higher than high definition (HD). The first image processing circuit 120_1 may extract all frames of the original image frame 111 in step S220 , and adjust the resolution of the extracted frames as the first image frame 140_1 . Here it is assumed that the resolution of the first image frame 140_1 is high resolution (HD). The first image processing circuit 120_1 can perform image recognition to find out the position of the license plate 310 of the vehicle from the original image frame 111 , and provide the position of the license plate 310 to the second image processing circuit 120_2 . According to the position of the license plate 310 provided by the first image processing circuit 120_1 , the second image processing circuit 120_2 can extract a part of the frame containing the license plate 310 from the original image frame 111 as the second sub-frame 320 . The second image processing circuit 120_2 can adjust the resolution of the second sub-frame 320 to obtain the second image frame 140_2 . Here it is assumed that the resolution of the second image frame 140_2 is high resolution (HD). That is to say, the second image processing circuit 120_2 can enlarge the partial frame of the license plate 320 in the original image frame 111 to form the second image frame 140_2 .

To sum up, the driving recorder 100 and its operating method according to the embodiment of the present invention can simultaneously provide the original image frame 111 generated by the same camera module 110 to different image processing circuits 120_1 , 120_2 and 120_3 . These different image processing circuits 120_1 , 120_2 and 120_3 respectively extract and generate different image frames 140_1 , 140_2 and 140_3 from the original image frame 111 with different viewing angles. Therefore, the driving recorder 100 and its operating method can use a single lens to capture multiple image frames from different viewing angles.

FIG. 4 is a schematic circuit block diagram illustrating a driving recorder 400 according to another embodiment of the present invention. For the driving recorder 400 shown in FIG. 4 , reference may be made to the relevant descriptions of the driving recorder 100 shown in FIG. 1 , or to the relevant descriptions of FIGS. 2 and 3 , and so on. The driving recorder 400 includes a camera module 110 , a first image processing circuit 120_1 , a second image processing circuit 120_2 and a database 130 . In the embodiment shown in FIG. 4, the first image processing circuit 120_1 includes a first image extraction circuit 421 and a first image scaling circuit 422, and the second image processing circuit 120_2 includes a second image extraction circuit 423 and a second image scaling circuit 424.

An input terminal of the first image capture circuit 421 is coupled to the camera module 110 to receive the original image frame 111 . The first image extraction circuit 421 can extract the first sub-image from the original image frame 111 . The input end of the first image scaling circuit 422 is coupled to the output end of the first image extraction circuit 421 . The first image scaling circuit 422 can adjust the resolution of the first sub-frame to obtain the first image frame 140_1 .

The input end of the second image extraction circuit 423 is coupled to the camera module 110 to receive the original image frame 111 . The second image extraction circuit 423 can extract the second sub-image from the original image frame 111 . The input end of the second image scaling circuit 424 is coupled to the output end of the second image extraction circuit 423 . The second image scaling circuit 424 can adjust the resolution of the second sub-frame to obtain the second image frame 140_2 .

In some embodiments, the first image extraction circuit 421 can perform image recognition to find an object (such as a license plate of a vehicle or other interesting characteristic images or objects) from the original image frame 111, and extract an object from the original image frame 111. The first sprite that contains this object. The first image scaling circuit 422 can adjust the resolution of the first sub-frame to obtain the first image frame 140_1 . The second image extraction circuit 423 can perform image recognition to find another object (such as a human face or other objects) from the original image frame 111 . Next, the second image extraction circuit 423 may extract a partial frame containing the other object from the original image frame 111 as a second sub-frame. The second image scaling circuit 424 can adjust the resolution of the second sub-frame to obtain the second image frame 140_2 .

In other embodiments, the first image extraction circuit 421 may extract all frames of the original image frame 111 , and the first image scaling circuit 422 may adjust the resolution of the extracted frames to be the first image frame 140_1 . On the other hand, the first image extraction circuit 421 can perform image recognition to find out the position of an object (such as a vehicle, a license plate, a human face, or other interesting characteristic images or objects) from the original image frame 111, and extract the object The position of is provided to the second image extraction circuit 423. According to the position of the object provided by the first image extraction circuit 421, the second image extraction circuit 423 can extract the second sub-picture containing the object from the original image frame 111, and the second image scaling circuit 424 can adjust the second sub-picture. The resolution of the sub-picture is taken as the second image picture 140_2.

In summary, the driving recorder 400 and its operating method according to the embodiment of the present invention can provide the original image frame 111 generated by the same camera module 110 to different image processing circuits 120_1 and 120_2 at the same time. These different image processing circuits 120_1 and 120_2 respectively extract and generate different image frames 140_1 and 140_2 from the original image frame 111 with different viewing angles. Therefore, the driving recorder 400 and its operation method can use a single lens to capture multiple image frames with different viewing angles.

Although the present invention has been disclosed as above with the embodiments, it is not intended to limit the present invention. Those skilled in the art can make some changes and modifications without departing from the spirit and scope of the present invention, so the protection scope of the present invention The scope defined by the appended claims shall prevail.

Claims (16)

1. A driving recorder, characterized in that, said driving recorder comprises: The camera module is configured to shoot a scene and output an original image frame; The first image processing circuit is coupled to the camera module to directly receive the original image frame from the camera module, and is configured to extract the original image frame from a first viewing angle to generate a first image frame, and record the first image frame in the database; and The second image processing circuit is coupled to the camera module to directly receive the original image frame from the camera module, and is configured to extract the original image frame with a second viewing angle to generate a second image frame, and record the second image frame in the database, wherein the second viewing angle of the second image frame is different from the first viewing angle of the first image frame, Wherein the first image processing circuit and the second image processing circuit simultaneously receive the original image frame, Wherein the first image processing circuit and the second image processing circuit respectively adjust the resolution of the first image frame and the resolution of the second image frame, so that the resolution of the first image frame and the second image frame The resolution is smaller than the resolution of the original image frame, so that the bandwidth resources provided by the database meet the bandwidth requirements for recording the first image frame and the second image frame in the database. 2. The driving recorder according to claim 1, wherein the original image frame is a wide-angle image. 3. The driving recorder according to claim 1, wherein the first image processing circuit comprises: A first image extraction circuit, whose input terminal is coupled to the camera module to receive the original image frame, is configured to extract a first sub-frame from the original image frame; and The input end of the first image scaling circuit is coupled to the output end of the first image extraction circuit, configured to adjust the resolution of the first sub-frame to obtain the first image frame. 4. The driving recorder according to claim 1, wherein the first image processing circuit performs image recognition to find an object from the original image frame, and extracts the first image containing the object from the original image frame. sprite. 5. The driving recorder as claimed in claim 4, wherein the object is a vehicle, a license plate or a human face. 6. The driving recorder according to claim 1, wherein the second image processing circuit comprises: The second image extraction circuit, whose input terminal is coupled to the camera module to receive the original image frame, is configured to extract a second sub-frame from the original image frame; and The second image scaling circuit, the input end of which is coupled to the output end of the second image extraction circuit, is configured to adjust the resolution of the second sub-image to obtain the second image frame. 7. The driving recorder according to claim 1, wherein the first image processing circuit generates the first image frame according to the entire original image frame; the first image processing circuit performs image recognition to obtain The image frame finds out the position of the object, and provides the position of the object to the second image processing circuit; and the second image processing circuit extracts from the original image frame according to the position of the object provided by the first image processing circuit The second sub-frame containing the object is used as the second image frame. 8. The driving recorder of claim 1, wherein the driving recorder further comprises: The third image processing circuit is coupled to the camera module to directly receive the original image frame from the camera module, and is configured to extract the original image frame from a third viewing angle to generate a third image frame, and record the third image frame In the database, the third viewing angle of the third image frame is different from the first viewing angle of the first image frame and the second viewing angle of the second image frame. 9. An operating method of a driving recorder, characterized in that the operating method comprises: The scene is photographed by the camera module and an original image frame is generated; Extracting the original image frame with a first viewing angle by the first image processing circuit to generate a first image frame, and recording the first image frame in a database; and The second image processing circuit extracts the original image frame with a second viewing angle to generate a second image frame, and records the second image frame in the database, wherein the second viewing angle of the second image frame is different from the first The first angle of view of the image frame, Wherein the first image processing circuit and the second image processing circuit directly and simultaneously receive the original image frame, Wherein the first image processing circuit and the second image processing circuit respectively adjust the resolution of the first image frame and the resolution of the second image frame, so that the resolution of the first image frame and the second image frame The resolution is smaller than the resolution of the original image frame, so that the bandwidth resources provided by the database meet the bandwidth requirements for recording the first image frame and the second image frame in the database. 10. The method for operating a driving recorder according to claim 9, wherein the original image frame is a wide-angle image. 11. The operation method of the driving recorder according to claim 9, wherein the step of generating the first image frame comprises: extracting a first sub-frame from the original image frame; and The resolution of the first sub-frame is adjusted to obtain the first image frame. 12. The operation method of the driving recorder according to claim 9, wherein the step of generating the first image frame comprises: perform image recognition to locate objects from the original image frame; and A first sub-frame containing the object is extracted from the original image frame. 13. The operating method of a driving recorder as claimed in claim 12, wherein the object is a vehicle, a license plate or a human face. 14. The operation method of the driving recorder according to claim 9, wherein the step of generating the second image frame comprises: extracting a second sub-frame from the original image frame; and The resolution of the second sub-frame is adjusted to obtain the second image frame. 15. The operation method of the driving recorder as claimed in claim 9, characterized in that: The step of generating the first image frame includes: generating the first image frame according to all the original image frames; and performing image recognition to find out the position of an object from the original image frame, and providing the position of the object to the second image processing circuit; and The step of generating the second image frame includes: According to the position of the object provided by the first image processing circuit, a second sub-frame containing the object is extracted from the original image frame as the second image frame. 16. The operation method of the driving recorder according to claim 9, characterized in that, the operation method further comprises: Extracting the original image frame with a third viewing angle by a third image processing circuit to generate a third image frame, and recording the third image frame in the database, wherein the third viewing angle of the third image frame is different from the first The first viewing angle of the image frame and the second viewing angle of the second image frame.