WeBox: locating small objects from weak edges

Abstract

In the object detection task, how to better deal with small objects is a great challenge. The detection accuracy of small objects greatly affects the final detection performance. Our propose a detection framework WeBox based on weak edges for small object detection in dense scenes, and proposes to train the richer convolutional features (RCF) edges detection network in a weakly supervised way to generate multi-instance proposals. Then through the region proposal network (RPN) network to locate each object in the multi-instance proposals, in order to ensure the effectiveness of the multi-instance proposals, we correspondingly proposed a multi-instance proposals evaluation criterion. Finally, we use faster region-based convolutional neural network (R-CNN) to process WeBox single-instance proposals and fine-tune the final results at the pixel level. The experiments have been carried out on BDCI and TT100K proves that our method maintains high computational efficiency while effectively improving the accuracy of small objects detection.

References

[1] RenS, HeK, GirshickR, SunJ. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 6: 1137

[2] Joseph Redmon, Santosh Divvala, Ross Girshick and Ali Farhadi, IEEE Conference on Computer Vision and Pattern Recognition, 2016.

[3] Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu and Alexander C. Berg, SSD: Single Shot MultiBox Detector, European Conference on Computer Vision, 21 (2016).

[4] JinJ, FuK, ZhangC. IEEE Transactions on Intelligent Transportation Systems, 2014, 15: 1991

[5] Tam T. Le, Son T. Tran, Seichii Mita and Thuc D. Nguyen, Real Time Traffic Sign Detection Using Color and Shape-Based Features, Asian Conference on Intelligent Information and Database Systems, 268 (2010).

[6] ZhuY, ZhangC, ZhouD, WangX, BaiX, LiuW. Neurocomputing, 2016, 214: 758

[7] Yonglong Tian, Ping Luo, Xiaogang Wang and Xiaoou Tang, Pedestrian Detection Aided by Deep Learning Semantic Tasks, IEEE Conference on Computer Vision and Pattern Recognition, 2015.

[8] Liliang Zhang, Liang Lin, Xiaodan Liang and Kaiming He, Is Faster R-CNN Doing Well for Pedestrian Detection? European Conference on Computer Vision, (443) 2016.

[9] Tsung-Yi Lin, Piotr Dollar, Ross Girshick, Kaiming He, Bharath Hariharan and Serge Belongie, Feature Pyramid Networks for Object Detection, IEEE Conference on Computer Vision and Pattern Recognition, 2017.

[10] Zhaowei Cai, Nuno Vasconcelos, Cascade R-CNN: Delving into High Quality Object Detection, Computer Vision and Pattern Recognition, 2017.

[11] Jianan Li, Xiaodan Liang, Yunchao Wei, Tingfa Xu, Jiashi Feng and Shuicheng Yan, Perceptual Generative Adversarial Networks for Small Object Detection, Computer Vision and Pattern Recognition, 2017.

[12] Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Den and Jian Sun, DetNet: A Backbone Network for Object Detection, Computer Vision and Pattern Recognition, 2018.

[13] LiuY, ChengM-M, HuX, BianJ-W, ZhangL, BaiX, TangJ. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41: 1939

[14] Peng Cheng, Wu Liu, Yifan Zhang and Huadong Ma, LOCO: Local Context Based Faster R-CNN for Small Traffic Sign Detection, International Conference on Multimedia Modeling, (329) 2018.