Border-oriented post-processing refinement on detected vehicle bounding box for ADAS

Xinyuan Chen; Zhaoning Zhang; Minne Li; Dongsheng Li

doi:10.1117/12.2305330

10 April 2018 Border-oriented post-processing refinement on detected vehicle bounding box for ADAS

Xinyuan Chen, Zhaoning Zhang, Minne Li, Dongsheng Li

Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 106150B (2018) https://doi.org/10.1117/12.2305330
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China

Abstract

We investigate a new approach for improving localization accuracy of detected vehicles for object detection in advanced driver assistance systems(ADAS). Specifically, we implement a bounding box refinement as a post-processing of the state-of-the-art object detectors (Faster R-CNN, YOLOv2, etc.). The bounding box refinement is achieved by individually adjusting each border of the detected bounding box to its target location using a regression method. We use HOG features which perform well on the edge detection of vehicles to train the regressor and the regressor is independent of the CNN-based object detectors. Experiment results on the KITTI 2012 benchmark show that we can achieve up to 6% improvements over YOLOv2 and Faster R-CNN object detectors on the IoU threshold of 0.8. Also, the proposed refinement framework is computationally light, allowing for processing one bounding box within a few milliseconds on CPU. Further, this refinement method can be added to any object detectors, especially those with high speed but less accuracy.

Citation Download Citation

Xinyuan Chen, Zhaoning Zhang, Minne Li, and Dongsheng Li "Border-oriented post-processing refinement on detected vehicle bounding box for ADAS", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106150B (10 April 2018); https://doi.org/10.1117/12.2305330

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available