CN204206364U - A kind of Yunnan snub-nosed monkey device based on binocular camera - Google Patents
A kind of Yunnan snub-nosed monkey device based on binocular camera Download PDFInfo
- Publication number
- CN204206364U CN204206364U CN201420708906.4U CN201420708906U CN204206364U CN 204206364 U CN204206364 U CN 204206364U CN 201420708906 U CN201420708906 U CN 201420708906U CN 204206364 U CN204206364 U CN 204206364U
- Authority
- CN
- China
- Prior art keywords
- video
- binocular camera
- image
- video image
- nosed monkey
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Abstract
The utility model discloses a kind of Yunnan snub-nosed monkey device based on binocular camera, its device body comprises video image preprocessor, image buffer memory, video input terminal and video output terminal, video image preprocessor is connected with image buffer memory, video image preprocessor signal input part and video inputs sub-connection, video image preprocessor signal output part and video output terminals sub-connection; Outside binocular camera is connected to the video input terminal of described device by communication cable, the external computing device generated for stereo scene depth map is connected to the video output terminal of described device by communication cable.Pass through the utility model, for the stereo scene detection product based on binocular camera adds Yunnan snub-nosed monkey device, the part process of scene detection neutral body matching algorithm is carried out computing by Yunnan snub-nosed monkey device in advance, save a large amount of computing overhead, promote the operating efficiency of stereo scene detection product.
Description
Technical field
The utility model relates to field of picture communication, particularly relates to a kind of Yunnan snub-nosed monkey device based on binocular camera.
Background technology
Binocular camera is carried out shooting to a scene by two imaging apparatuss installed with different angles simultaneously and is obtained two-way image, due to three-dimensional depth information can be obtained by Stereo Matching Algorithm from image, cost is low, and binocular camera comes into one's own in stereo scene Detection Techniques.
The Stereo Matching Algorithm that binocular camera is used, the coupling needing the two-way image of camera to acquire a certain degree could realize, but by the impact of many uncontrollable factors such as camera lens, environment cleanliness, loss, A/D conversion accuracy, the two-way image of binocular camera usually has certain difference in picture noise, color space, pattern distortion etc., and difference value is difficult to prediction; Due to the existence of this problem, when binocular camera is used for stereo scene detection, usually with backend computer, preliminary treatment is carried out to two-way image, make it the needs meeting Stereo Matching Algorithm, but this mode occupies rear end computational resource, when computing capability is not enough, the real-time of stereo scene detection will be greatly affected.
Summary of the invention
For promoting the stereo scene detectivity of binocular camera, the utility model proposes and a kind ofly preliminary treatment binocular camera can gather the Yunnan snub-nosed monkey device of image.
The utility model adopts following scheme: a kind of Yunnan snub-nosed monkey device based on binocular camera, it is characterized in that: it comprises video image preprocessor, image buffer memory, video input terminal and video output terminal, video image preprocessor is connected with image buffer memory, video image preprocessor signal input part and video inputs sub-connection, video image preprocessor signal output part and video output terminals sub-connection; Outside binocular camera is connected to the video input terminal of described device by communication cable, the external computing device generated for stereo scene depth map is connected to the video output terminal of described device by communication cable.
Described video image preprocessor, is provided with image collection circuit.
Described video image preprocessor, is provided with image synchronous circuit.
Described video image preprocessor, is provided with image correction circuit.
Described video image preprocessor, is provided with image-zooming circuit.
Described video image preprocessor, is provided with Imaging enhanced circuit.
Described video image preprocessor, is provided with color conversion circuit.
Described video image preprocessor, is provided with controller, controls video image preprocessor and is connected with the communication between image buffer memory.
Described video inputs subnumber is one or two, receives the image of outside binocular camera, and video output terminals subnumber is 1.
The utility model is mainly used in stereo scene detection, utilizes video image Pre-processing hardware to the preliminary treatment of the aspect such as the collection correct image of scene detection binocular camera, filtering, synchronous, convergent-divergent, Imaging enhanced and color conversion, has the following advantages:
1, with special Yunnan snub-nosed monkey device, preliminary treatment is carried out to camera image, alleviate the calculating pressure that external computing device runs Stereo Matching Algorithm.
2, by conjunction with Yunnan snub-nosed monkey device and the external computing device generated for stereo scene depth map, improve the real time execution ability of Stereo Matching Algorithm, high-quality scene steric information can be obtained.
3, Yunnan snub-nosed monkey device uses the hardware logic of IC device to the parallel processing of two-way image, and processing speed is fast and stable.
4, by the preliminary treatment of Yunnan snub-nosed monkey device, can also compress the video data of binocular camera, reduce network and take, improve the data transmission capabilities between external computing device and binocular camera.
5, Yunnan snub-nosed monkey device is hardware device, its working method is comparatively fixing, and external computing device is generally SoC or CPU arithmetic facility, a part for Stereo Matching Algorithm is run with software mode, its working method and performance are comparatively flexible, therefore pass through the concrete division of labor of reasonable arrangement Yunnan snub-nosed monkey device and rear end computing platform, different Stereo Matching Algorithm demands can be adapted to.
Accompanying drawing explanation
Below in conjunction with accompanying drawing to the further detailed description of the utility model:
Fig. 1 is the system architecture schematic diagram of a kind of Yunnan snub-nosed monkey device based on binocular camera described in the utility model;
Fig. 2 is video image preprocessor internal circuit blocks block diagram described in the utility model.
Embodiment
As shown in Figure 1, the utility model comprises video image preprocessor 4, image buffer memory 5, video input terminal 6 and 8, video output terminal 7, video image preprocessor 4 is connected with image buffer memory 5, video image preprocessor 4 signal input part is connected with video input terminal 6 and 8, video image preprocessor 4 signal output part is connected with video output terminal 7, outside binocular camera 1 is connected to the video input terminal 6 of described device by communication cable, 8, the external computing device 3 generated for stereo scene depth map to be connected to the video output terminal 7 of described device by communication cable.
As shown in Figure 2, described video image preprocessor 4, is provided with image collection circuit 21.
As shown in Figure 2, described video image preprocessor 4, is provided with image synchronous circuit 22.
As shown in Figure 2, described video image preprocessor 4, is provided with image correction circuit 23.
As shown in Figure 2, described video image preprocessor 4, is provided with image-zooming circuit 24.
As shown in Figure 2, described video image preprocessor 4, is provided with Imaging enhanced circuit 25.
As shown in Figure 2, described video image preprocessor 4, is provided with color conversion circuit 26.
As shown in Figure 2, described video image preprocessor 4, is provided with controller 27, controls video image preprocessor 4 and is connected with the communication between image buffer memory 5.
As shown in Figure 1, described Yunnan snub-nosed monkey device video inputs subnumber is two, and receive the image of outside binocular camera 1, video output terminals subnumber is 1, and diagram video input terminal is terminal 6, terminal 8, and video output terminal is terminal 7.
As shown in Figure 1, two imaging apparatuss of binocular camera 1 gather image R, the image L of different visual angles respectively, the image collected sends into Yunnan snub-nosed monkey device through video input terminal 6,8, the built-in image buffer memory of Yunnan snub-nosed monkey device 5 pairs of image datas carry out buffer memory, Yunnan snub-nosed monkey device built in video image pre-processor 4 pairs of image datas carry out preliminary treatment, are transferred to the correlation computations that external computing device 3 carries out stereo scene detection through the revised L/R image information of preliminary treatment through video output terminal 7.
In the present embodiment, video input terminal 6,8 inputs the two-path video data of camera, and video output terminal 7 exports pretreated image data to the external computing device 3 generated for stereo scene depth map.
As shown in Figure 2, in video image preprocessor 4, image collection circuit 21, image synchronous circuit 22, image correction circuit 23, image-zooming circuit 24, Imaging enhanced circuit 25, color conversion circuit 26 are connected with described image buffer memory 5 by controller 27.
As shown in Figure 2, in the present embodiment, after the vision signal arrival video image preprocessor 4 of image L, R input, first deliver to image collection circuit 21, image collection circuit sends signal to controller 27, shows that video image preprocessor 4 starts video pre-filtering process, by controller 27, video data stored in image buffer memory 5, send video pre-filtering signal to image synchronous circuit 22 simultaneously.
After image synchronous circuit 22 receives video pre-filtering signal, by controller 27, obtain from image buffer memory 5 image collection circuit 21 stored in video data, by parameter preset, by the School Affairs correction to frame of video, make the video frame transmission of two parts digital video can realize synchronously, and after ending process, by controller 27, video data stored in image buffer memory 5, send video pre-filtering signal to image correction circuit 23 simultaneously.
After image correction circuit 23 receives video pre-filtering signal, by controller 27, obtain from image buffer memory 5 image synchronous circuit 22 stored in video data, by parameter preset, geometric correction is carried out to video image, and after ending process, by controller 27, video data stored in image buffer memory 5, send video pre-filtering signal to image-zooming circuit 24 simultaneously.
After image-zooming circuit 24 receives video pre-filtering signal, by controller 27, obtain from image buffer memory 5 image correction circuit 23 stored in video data, by parameter preset, convergent-divergent process is done to video image, and after ending process, by controller 27, video data stored in image buffer memory 5, send video pre-filtering signal to Imaging enhanced circuit 25 simultaneously.
After Imaging enhanced circuit 25 receives video pre-filtering signal, by controller 27, obtain from image buffer memory 5 image-zooming circuit 24 stored in video data, by parameter preset, image feature intensive treatment is carried out to video image, as filtering, contrast strengthen, sharpening, noise reduction etc., and after ending process, by controller 27, video data stored in image buffer memory 5, send video pre-filtering signal to color conversion circuit 26 simultaneously.
After color conversion circuit 26 receives video pre-filtering signal, by controller 27, obtain from image buffer memory 5 Imaging enhanced circuit 25 stored in video data, by parameter preset, video image is carried out to the conversion of color space, as rgb color is converted to YUV, or chromatic image is converted to grayscale image etc., after ending process, instruction is sent to controller 27, show that the video pre-filtering process of this video image preprocessor 4 terminates, and the video data after process is sent video image preprocessor 4.
In the present embodiment, video image preprocessor 4 is similar FPGA programmable logic device or the IC device possessing corresponding function, and the hardware logic of employing device realizes the process to image, to improve the speed of service, reaches the target of real-time operation.
In the present embodiment, the output of Yunnan snub-nosed monkey device meets that specific Stereo Matching Algorithm requires, the image data after optimization process such as color and size, and the CPU/SOC sending external computing device 3 to by video output terminal 7 carries out all the other computings of Stereo matching.Because Yunnan snub-nosed monkey device is for a large amount of preliminary treatment has been done in Stereo matching computing, therefore, the CPU/SOC of external computing device 3 can save a large amount of computing overhead.The CPU/SOC of external computing device 3 can carry out all the other computings of Stereo Matching Algorithm by pooling of resources, improves the efficiency of stereo scene detection.
Technical characterstic of the present utility model is for the stereo scene detection product based on binocular camera adds Yunnan snub-nosed monkey device, and the part process of scene detection neutral body matching algorithm is carried out computing by Yunnan snub-nosed monkey device in advance.It should be noted that, according to the requirement of selected Stereo Matching Algorithm, the computing that Yunnan snub-nosed monkey device described in the utility model carries out, structure, framework, and the computing module comprised can be different.Just exemplarily, every employing similar system framework is used for the product of stereo scene detection to accompanying drawing in the utility model, is all claim place of the present utility model.
Claims (9)
1. the Yunnan snub-nosed monkey device based on binocular camera, it is characterized in that: it comprises video image preprocessor, image buffer memory, video input terminal and video output terminal, video image preprocessor is connected with image buffer memory, video image preprocessor signal input part and video inputs sub-connection, video image preprocessor signal output part and video output terminals sub-connection; Outside binocular camera is connected to the video input terminal of described device by communication cable, the external computing device generated for stereo scene depth map is connected to the video output terminal of described device by communication cable.
2. a kind of Yunnan snub-nosed monkey device based on binocular camera according to claim 1, is characterized in that: described video image preprocessor, is provided with image collection circuit.
3. a kind of Yunnan snub-nosed monkey device based on binocular camera according to claim 1, is characterized in that: described video image preprocessor, is provided with image synchronous circuit.
4. a kind of Yunnan snub-nosed monkey device based on binocular camera according to claim 1, is characterized in that: described video image preprocessor, is provided with image correction circuit.
5. a kind of Yunnan snub-nosed monkey device based on binocular camera according to claim 1, is characterized in that: described video image preprocessor, is provided with image-zooming circuit.
6. a kind of Yunnan snub-nosed monkey device based on binocular camera according to claim 1, is characterized in that: described video image preprocessor, is provided with Imaging enhanced circuit.
7. a kind of Yunnan snub-nosed monkey device based on binocular camera according to claim 1, is characterized in that: described video image preprocessor, is provided with color conversion circuit.
8. a kind of Yunnan snub-nosed monkey device based on binocular camera according to claim 1, is characterized in that: described video image preprocessor is provided with controller, controls video image preprocessor and is connected with the communication between image buffer memory.
9. a kind of Yunnan snub-nosed monkey device based on binocular camera according to claim 1, is characterized in that: described video inputs subnumber is one or two, and receive the image of outside binocular camera, video output terminals subnumber is 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420708906.4U CN204206364U (en) | 2014-11-21 | 2014-11-21 | A kind of Yunnan snub-nosed monkey device based on binocular camera |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420708906.4U CN204206364U (en) | 2014-11-21 | 2014-11-21 | A kind of Yunnan snub-nosed monkey device based on binocular camera |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN204206364U true CN204206364U (en) | 2015-03-11 |
Family
ID=52664271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201420708906.4U Expired - Fee Related CN204206364U (en) | 2014-11-21 | 2014-11-21 | A kind of Yunnan snub-nosed monkey device based on binocular camera |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN204206364U (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107230187A (en) * | 2016-03-25 | 2017-10-03 | 北京三星通信技术研究有限公司 | The method and apparatus of multimedia signal processing |
| CN111614898A (en) * | 2016-10-05 | 2020-09-01 | 三星电子株式会社 | Image processing system |
| CN111770382A (en) * | 2019-04-02 | 2020-10-13 | 瑞昱半导体股份有限公司 | Video processing circuit and method for processing multiple videos using a single video processing path |
| CN111836030A (en) * | 2019-04-17 | 2020-10-27 | 未来市股份有限公司 | Interactive image processing method, apparatus and medium using depth engine |
| CN111836035A (en) * | 2019-04-17 | 2020-10-27 | 未来市股份有限公司 | Interactive image processing method and device and storage device |
| CN111836034A (en) * | 2019-04-17 | 2020-10-27 | 未来市股份有限公司 | Interactive image processing system using infrared camera |
| US11962906B2 (en) | 2016-10-05 | 2024-04-16 | Samsung Electronics Co., Ltd. | Image processing systems for correcting processed images using image sensors |
-
2014
- 2014-11-21 CN CN201420708906.4U patent/CN204206364U/en not_active Expired - Fee Related
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107230187A (en) * | 2016-03-25 | 2017-10-03 | 北京三星通信技术研究有限公司 | The method and apparatus of multimedia signal processing |
| US11081137B2 (en) | 2016-03-25 | 2021-08-03 | Samsung Electronics Co., Ltd | Method and device for processing multimedia information |
| CN107230187B (en) * | 2016-03-25 | 2022-05-24 | 北京三星通信技术研究有限公司 | Method and device for processing multimedia information |
| CN111614898A (en) * | 2016-10-05 | 2020-09-01 | 三星电子株式会社 | Image processing system |
| US11190700B2 (en) | 2016-10-05 | 2021-11-30 | Samsung Electronics Co., Ltd. | Image processing systems for correcting processed images using image sensors |
| CN111614898B (en) * | 2016-10-05 | 2022-04-05 | 三星电子株式会社 | Image processing system |
| US11962906B2 (en) | 2016-10-05 | 2024-04-16 | Samsung Electronics Co., Ltd. | Image processing systems for correcting processed images using image sensors |
| CN111770382A (en) * | 2019-04-02 | 2020-10-13 | 瑞昱半导体股份有限公司 | Video processing circuit and method for processing multiple videos using a single video processing path |
| CN111836030A (en) * | 2019-04-17 | 2020-10-27 | 未来市股份有限公司 | Interactive image processing method, apparatus and medium using depth engine |
| CN111836035A (en) * | 2019-04-17 | 2020-10-27 | 未来市股份有限公司 | Interactive image processing method and device and storage device |
| CN111836034A (en) * | 2019-04-17 | 2020-10-27 | 未来市股份有限公司 | Interactive image processing system using infrared camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN204206364U (en) | A kind of Yunnan snub-nosed monkey device based on binocular camera | |
| CN103220545B (en) | Hardware implementation method of stereoscopic video real-time depth estimation system | |
| CN105631798B (en) | Low Power Consumption Portable realtime graphic object detecting and tracking system and method | |
| CN107636680B (en) | Obstacle detection method and device | |
| CN108255773A (en) | A kind of intelligence computation heterogeneous polynuclear processing method and platform | |
| CN112153306B (en) | Image acquisition system, method and device, electronic equipment and wearable equipment | |
| US10417771B2 (en) | Fast MRF energy optimization for solving scene labeling problems | |
| CN103116872B (en) | Based on SAR image high_speed stamping die and the method thereof of Parallel DSP | |
| WO2019015415A1 (en) | Method of living body detection and terminal device | |
| US10445402B1 (en) | Fast and energy-efficient region of interest pooling for object detection with convolutional neural network | |
| CN103985083B (en) | Reconfigurable one-dimensional convolution processor | |
| CN103888751A (en) | Embedded type panoramic three-dimensional spherical visual image acquisition system based on DSP | |
| CN103473807A (en) | 3D model transformation system and method | |
| CN104715470A (en) | Klt corner point detecting device and method | |
| Fularz et al. | The architecture of an embedded smart camera for intelligent inspection and surveillance | |
| CN116468917A (en) | Image processing method, electronic device and storage medium | |
| US10187623B2 (en) | Stereo vision SoC and processing method thereof | |
| Wu et al. | The development and implementation of a real-time depth image capturing system using SoC FPGA | |
| CN103369338B (en) | Based on image processing system and the method for the nearly eye binocular imaging system of FPGA | |
| US11619498B2 (en) | Verification method and device for modeling route, unmanned vehicle, and storage medium | |
| CN107452026A (en) | A kind of processing system and its method for image spot barycenter | |
| CN111314660A (en) | Video signal processing method and system applied to ultrahigh-definition video picture cutting | |
| CN111161397A (en) | Face three-dimensional reconstruction method and device, electronic equipment and readable storage medium | |
| Prakash et al. | FPGA Based Lane Tracking system for Autonomous Vehicles | |
| CN113487487B (en) | Super-resolution reconstruction method and system for heterogeneous stereo image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20150311 Termination date: 20201121 |