Improved YOLOv3 Model for miniature camera detection

Abstract The abuse of miniature cameras has severely violated information security and privacy. Several unsolved challenges such as small or multiple targets detection as well as complex background environments in terms of active laser detection still exist, resulting in difficulties in its practical application. In this paper, an active laser detection system is proposed to obtain high-intensity cat-eye reflection images. An improved YOLOv3 model, YOLOv3-4L, was introduced to detect the actual position of the target. In the YOLOv3-4L model, each image was resized to 608 × 608 to preserve image details. The scales of prediction were increased from three to four, and an additional feature map was used to extract more details. YOLOv3-4L exhibited excellent performance in detecting small targets. The experimental results show that the mean average precision achieved by YOLOv3-4L was 90.37 % , compared to the 85.41 % , 87.81 % , and 88.97 % achieved by traditional YOLOv3, Faster R-CNN, and Single Shot Multi-box Detector respectively. The speed of the YOLOv3-4L model meets the requirements of real-time target detection.

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

[2]  Mali Gong,et al.  Periodicity analysis on cat-eye reflected beam profiles of optical detectors , 2017 .

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

[4]  Mali Gong,et al.  Cat-eye effect reflected beam profiles of an optical system with sensor array. , 2016, Applied optics.

[5]  Zilong Zhang,et al.  Spectrum classification using convolutional neural networks for a mini-camera detection system. , 2019, Applied optics.

[6]  Chun Liu,et al.  Design of an Active Laser Mini-Camera Detection System Using CNN , 2019, IEEE Photonics Journal.

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

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

[10]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[11]  Baiwei Mao,et al.  Ultra-Broadband Mode Converter Using Cascading Chirped Long-Period Fiber Grating , 2019, IEEE Photonics Journal.

[12]  Qiu-Yan Song,et al.  Time- and wavelength-division multiplex distributed sensing interrogation system based on distributed feedback laser array and ultraweak fiber Bragg grating , 2017 .

[13]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[15]  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.

[16]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.