With the progress of artificial intelligence (AI) technology, social implementation such as image recognition using AI technology, automatic driving, and natural language processing is rapidly progressing. Especially in the edge computing field, since it is necessary to realize AI technology with higher efficiency, startups mainly in the United States and China and major vendors are accelerating their entry into AI hardware, and even in Japan Not only that, there is an urgent need to develop human resources and industries for hardware to accelerate AI processing such as LSI and FPGA.
Against this background, we will carry out this contest, in addition to the conventional AI technology development centered on software, we are aiming to develop human resources and startups with AI hardware in mind, as well as industry development utilizing these technologies. In this contest, we will develop AI hardware equipped with the "RISC-V" chip, which is currently attracting attention, and set the hardware system development that considers edge computing including hardware and software (network model and system optimization) as an issue.
The 1st AI Edge Contest (Algorithm Contest (1))
The 2nd AI Edge Contest (Implementation Contest (1))
The 3rd AI Edge Contest (Algorithm Contest (2))
The 4th AI Edge Contest (Implementation Contest (2))
*Please refer to the winners' solutions in the past AI edge contest.
(Algorithm development) Create an algorithm that detects a rectangular area in which objects are captured from the videos taken by a camera forward facing a vehicle and tracks the objects.|
(Algorithm implementation) Design hardware accelerators and implement algorithm on the target platform equipped with RISC-V.
|Provided data||(Train/Test) videos of a vehicle front camera|
(Train) Rectangular tag area labeled with objects, category and object ID
|Identifying target||Car, Pedestrian|
|Implementation||Using RISC-V in the processing of object tracking（For the details, please refer to the Rules）|
|Award||Processing speed award||Idea award|
|Platform||Avnet Ultra96-V2 FPGA board<
（Zynq UltraScale+ MPSoC ZAU3EG SBVA484）
|Evaluation||Processing speed of the target FPGA board
||RISC-V utilization ideas|
|Winning requirements||The MOTA of the object tracking result of the test data is over 0.6, etc.
||It is not difficult to apply it practically, such as the MOTA of the object tracking result of the test data is much lower than 0.6 (less than half).|
|Final result set||Source code, area report, implementation approach, processing performance, etc.
||Source code, implementation report, video of the operation, etc.|
|Prize.||TBD (top 3 teams)||TBD（Up to 3 teams）|
|Special prize||Forum Activity Award / Article Writing Award|
|TBD（Up to 3 teams）|
(Forum Activity Award) Those who have greatly contributed to solving the problem in the forum.
(Article Writing Award)Those who wrote articles with high educational effect on the Web on blogs etc. and published links on the forum.
Subject (Algorithm development)
Allocate a rectangular area containing objects to be predicted as a bounding box = (x1, y1, x2, y2) to the video captured by the vehicle front camera, and give any unique object ID to the same object in each video. With allocations of multiple bounding boxes to each frame in the videos, the bounding box is represented by specifying four coordinates with the upper left corner as the origin (0,0), upper left coordinate of the object area (x1, y1), and the lower right coordinate (x2, y2).
However, the object to be evaluated (objects to be inferred) is limited to those that satisfy all of the following.
・There are two categories: “Car” and “Pedestrian”
・Objects with 3 or more frames in each video (Frames do not have to be continuous)
・Objects with a rectangle size of 1024 pix² or more
*Even if an object appears in three or more frames in the video, if there are less than 1024 pix² or more in three frames, the object including the size of 1024 pix² or more will not be evaluated.
*Please note that if an object that does not meet the conditions is detected, it is considered as a false detection.
Subject (Algorithm Implementation)
Implement the developed algorithm on the target platform equipped with a RISC-V chip.
The section to be optimized and the processing time to be measured is defined as follows.
Time to perform inference processing on the video data loaded in the memory and then convert it to JSON-equivalent information such as the ID and rectangle information of each object.
Carefully check the RISC-V usage requirements described in the "Rules" tab before implementing.
|For Train||For Test|
|Route||Tokyo (Shibuya – Akihabara)|
|Time Zone||Day time|
|Resolution||1936 x 1216|
|Category Types||Car, Pedestrian, Truck, Signal, Signs, Bicycle, Motorbike, Bus, Svehicle, Train||Car, Pedestrian|
|Number of Videos||25 videos||74 videos|
|Length of an videos||120 seconds||30 seconds|
|Number of Frames per video||600||150|
Flow of entry / registration for the contest
1. Sign up for SIGNATE (Please register through the member registration button on the top right of the page if you are not currently a member.).
2. Download the data from the data tab (Please agree the terms of entry that will be displayed when downloading.).
3. Develop an algorithm and implement / optimize it on the selected target environment
* We plan to provide FPGA board to a maximum of 50 applicants based on the review of application among the people who apply through application form for the board offer document review. (The number of boards offered may increase.)
* If you do not have an Ultra96-V2 board and would like to use it as a target environment, please purchase it yourself or apply by clicking the button below.
4. During the contest, submit the object trakking result from the "Submit" button on the upper right of this page and check the MOTA score on the leaderboard.
* Please refer to the MOTA function that can be downloaded on the data page.
* The MOTA score until the last day of the contest (public score) and the MOTA score after the contest (private score) are the same.
5. (Optional) During the contest, we will submit the provisional processing time ranking as reference information, so please cooperate.
* Please submit the average processing time [ms] per video at the time of posting and the evaluation result by MOTA from the "Submit" button on the page that transitions from the following.
* Submits are accepted at any time until the deadline of 2022/1/15, and can be updated.(The latest results will be displayed)
* In the case of a team, the team leader should submit it as a representative. The user name of the poster is displayed on the interim processing time leaderboard.
6. Submit the final result set by the end of the contest.
* For details, refer to "submission_details.pdf" that can be downloaded from the data page.
* Upload on the Internet such as Dropbox, Gigafile, etc., and inform us of the information required for downloading to the following form.