Real-time object detection of optical image with a lightweight model

• Autorzy: Lve Huang , Chuxin Lin , Wenyan Xiao

Identyfikatory

DOI

10.37190/oa/194973

• Języki publikacji: EN

Abstrakty

EN

To process the massive optical image data collected in machine vision systems and address the limitations of current learning detection models for real-time processing, this paper proposes a lightweight and real-time detection model based on YOLOX-Nano. While YOLOX-Nano is a lightweight object detection model, its detection accuracy is relatively low. Thus, this paper focuses on ensuring a lightweight model while maintaining high accuracy. The improved model incorporates an attention mechanism based on spatial and channel features to enhance the feature extraction capability of the YOLOX-Nano model. Additionally, a dual decoupled feature fusion approach is introduced to further improve the weighted fusion of feature maps extracted at different levels. This approach addresses the issue of smaller objects being overlooked in multi-object detection and enhances detection accuracy. Compared with the YOLOX-Nano baseline model, the proposed model achieves a detection speed of 59.52 FPS (frames per second) while increasing the AP50:95 metric. It meets the requirements for real-time detection, which is suitable for deployment on embedded systems, enabling the requirements of miniaturized optical processing tasks.

Słowa kluczowe

EN

lightweight optical detection system; YOLOX-Nano; decoupled attention mechanism; DAM; dual decoupled feature fusion; DDFF

• Wydawca: Oficyna Wydawnicza Politechniki Wrocławskiej
• Czasopismo: Optica Applicata
• Rocznik: 2024
• Tom: Vol. 54, nr 4
• Strony: 567--579
• Opis fizyczny: Bibliogr. 21 poz., rys., tab.

Twórcy

autor

Lve Huang

• School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou 341000, Jiangxi, China

autor

Chuxin Lin

• School of Science, Jiangxi University of Science and Technology, Ganzhou 341000, Jiangxi, China

autor

Wenyan Xiao

• School of General Education, Jiangxi University of Science and Technology, Nanchang 330022, Jiangxi, China

Bibliografia

• [1] HUANG L.E., WU L.S., XIAO W.Y., PENG Q.J., Deblurring approach for motion camera combining FFT with α-confidence goal optimization, Optica Applicata 50(2), 2020: 185-198. https://doi.org/10.37190/oa200202
• [2] LIU J.J., YUAN J.Y., JIA Y.F., A new method for railway fastener detection using the symmetrical image and its EA-HOG feature, International Journal of Pattern Recognition and Artificial Intelligence 34(2), 2020: 2055006. https://doi.org/10.1142/S021800142055006X
• [3] WEI Y., TIAN Q., GUO J.H., HUANG W., CAO J., Multi-vehicle detection algorithm through combining Harr and HOG features, Mathematics and Computers in Simulation 155, 2019:130-145. https://doi.org/10.1016/j.matcom.2017.12.011
• [4] ZHAO Y.G., ZHENG F., SONG Z., Hand detection using cascade of softmax classifiers, Advances in Multimedia, Vol. 2018, 2018: 9204854. https://doi.org/10.1155/2018/9204854
• [5] HUANG D.Q., FU Y.Z., QIN N., GAO S.B., Fault diagnosis of high-speed train bogie based on LSTM neural network, Science China Information Sciences 64(1), 2021: 119203. https://doi.org/10.1007/s11432-018-9543-8
• [6] WEI R.Y., LI S.T., WU S.R., Defect detection of track fastener based on improved YOLO V3 algorithm, Railway Standard Design 64(12), 2020: 30-36.
• [7] GAO J.L., BAI T.B., YAO D.C., et al., Detection of track fastener based on improved YOLOv4 algorithm, Science Technology and Engineering 22(7), 2022: 2872-2877.
• [8] GE Z., LIU S.T., WANG F., LI Z.M., SUN J., YOLOX: Exceeding YOLO series in 2021, 2021, arXiv:2107.08430. https://doi.org/10.48550/arXiv.2107.08430
• [9] YAN B., FAN P., LEI X.Y., LIU Z.J., YANG F.Z., A real-time apple targets detection method for picking robot based on improved YOLOv5, Remote Sensing 13(9), 2021: 1619. https://doi.org/10.3390/rs13091619
• [10] LIU S., QI L., QIN H.F., Path aggregation network for instance segmentation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, USA: 8759-8768.
• [11] LIU S., HUANG D., WANG Y., Learning spatial fusion for single-shot object detection, 2019, arXiv:1911.09516. https://doi.org/10.48550/arXiv.1911.09516
• [12] HU J., QIAO P., LV H., OUYANG A., HE Y., LIU Y., High speed railway fastener defect detection by using improved YoLoX-Nano model, Sensors (Basel) 22(12), 2022: 8399-8415. https://doi.org/10.3390/s22218399
• [13] HU J., SHEN L., SUN G., Squeeze-and-excitation networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 18-23, 2018, Salt Lake City, USA: 7132-7141. https://doi.org/10.1109/CVPR.2018.00745
• [14] WOO S., PARK J., LEE J.Y., KWEON I.S., CBAM: Convolutional block attention module, [In] Ferrari V., Hebert M., Sminchisescu C., Weiss Y. [Eds.] Computer Vision – ECCV 2018, Lecture Notes in Computer Science, Vol. 11211, Springer, Cham. https://doi.org/10.1007/978-3-030-01234-2_1
• [15] HOU Q.B., ZHOU D.Q., FENG J.S., Coordinate attention for efficient mobile network design, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2021: 13713-13722. https://doi.org/10.1109/CVPR46437.2021.01350
• [16] ZHANG X., LIU Z., Fast color image encryption algorithm based on FCSM and pre-storage Arnold transform, Multimedia Tools and Applications 83(2), 2024: 3985-4016. https://doi.org/10.1007/s11042-023-15577-6
• [17] REN S.Q., HE K.M., GIRSHICK R., SUN J., Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Transactions on Pattern Analysis and Machine Intelligence 39(6), 2017: 1137-1149. https://doi.org/10.1109/TPAMI.2016.2577031
• [18] HE K.M., ZHANG X.Y., REN S.Q., SUN J., Deep residual learning for image recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016: 770-778.
• [19] SANDLER M., HOWARD A., ZHU M., ZHMOGINOV A., CHEN L.-C., MobileNetV2: Inverted residuals and linear bottlenecks, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018: 4510-4520. https://doi.org/10.1109/CVPR.2018.00474
• [20] ZHOU N., DENG J., PANG M., Recovering a clean background: A parallel deep network architecture for single-image deraining, Pattern Recognition Letters 178, 2024: 153-159. https://doi.org/10.1016/ j.patrec.2024.01.006
• [21] ZHANG H.Y., WANG Y., DAYOUB F., SÜNDERHAUF N., VarifocalNet: An IoU-aware dense object detector, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 2021: 8510-8519. https://doi.org/10.1109/CVPR46437.2021.00841