Significantly improving human detection in low-resolution images by retraining YOLOv3

Human detection in images is a crucial task due to its usage in different areas including person detection and identification, abnormal surveillance and crowd counting. Low-resolution of image sequences taken by stationary outdoor surveillance cameras is very challenging. Detecting human with deep learning techniques, is more powerful than traditional methods due to its ability to learn high-level deeper features, high detection accuracy and speed. Therefore, this paper proposes a method for human detection in low-resolution images based on YOLOv3. This method will prepare a dataset of low-resolution images collected by outdoor surveillance cameras and annotate them manually. Next, we retrain YOLOv3 to make an improved model for low-resolution images. The model achieves F1-score of 0.804 human detecting for low-resolution test images.

[1]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  En Li,et al.  Apple detection during different growth stages in orchards using the improved YOLO-V3 model , 2019, Comput. Electron. Agric..

[3]  Huang Jianjun,et al.  Human detection and tracking with deep convolutional neural networks under the constrained of noise and occluded scenes , 2020, Multimedia Tools and Applications.

[4]  William A. Hoff,et al.  Pedestrian detection in low resolution videos , 2014, IEEE Winter Conference on Applications of Computer Vision.

[5]  Liquan Zhao,et al.  Object Detection Algorithm Based on Improved YOLOv3 , 2020, Electronics.

[6]  Shaogang Gong,et al.  People detection in low-resolution video with non-stationary background , 2009, Image Vis. Comput..

[7]  Shawn Newsam,et al.  Motion-Aware Feature for Improved Video Anomaly Detection , 2019, BMVC.

[8]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Shengcai Liao,et al.  Face Recognition by Discriminant Analysis with Gabor Tensor Representation , 2007, ICB.

[10]  Awais Ahmad,et al.  Top view multiple people tracking by detection using deep SORT and YOLOv3 with transfer learning: within 5G infrastructure , 2020, International Journal of Machine Learning and Cybernetics.

[11]  Habibah Hashim,et al.  People Detection System Using YOLOv3 Algorithm , 2020, 2020 10th IEEE International Conference on Control System, Computing and Engineering (ICCSCE).

[12]  Xindong Wu,et al.  Object Detection With Deep Learning: A Review , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Mubarak Shah,et al.  Real-World Anomaly Detection in Surveillance Videos , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Wei Gong,et al.  Application of deep learning in object detection , 2017, 2017 IEEE/ACIS 16th International Conference on Computer and Information Science (ICIS).

[15]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Grantham Pang,et al.  People Counting and Human Detection in a Challenging Situation , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[17]  Dushyant Kumar Singh,et al.  Human detection techniques for real time surveillance: a comprehensive survey , 2020, Multimedia Tools and Applications.

[18]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[19]  Ramakant Nevatia,et al.  A multi-scale cascade fully convolutional network face detector , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[20]  Federico Cerutti,et al.  A Pilot Study on Detecting Violence in Videos Fusing Proxy Models , 2019, 2019 22th International Conference on Information Fusion (FUSION).

[21]  Manoranjan Paul,et al.  Human detection in surveillance videos and its applications - a review , 2013, EURASIP J. Adv. Signal Process..

[22]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[23]  Zhang Yi,et al.  An improved tiny-yolov3 pedestrian detection algorithm , 2019, Optik.

[24]  Pong C. Yuen,et al.  Very low resolution face recognition problem , 2010, 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS).

[25]  Fan Wu,et al.  Helmet Detection Based On Improved YOLO V3 Deep Model , 2019, 2019 IEEE 16th International Conference on Networking, Sensing and Control (ICNSC).