A novel email-based smart remote image surveillance camera

Abstract

Aiming at the problems of difficult deployment and access of surveillance system server, as well as high operation and maintenance cost, a remote surveillance camera is designed based on RK3566 chip, which is controlled and transmits data via email platform. Firstly, to address the impact of environmental factors such as weather and light on image quality, a deep neural network (DNN) image exposure correction network is employed to rectify images with abnormal exposure. Additionally, a back propagation (BP) neural network is utilized to fit a curve relating the brightness difference to the gamma value of images before and after exposure correction, thereby adjusting the gamma value of the camera. Secondly, to enhance the precision of YOLOv5 algorithm in differentiating between anomalies in nighttime imagery, infrared image data are employed, and a context-aware light-weight label assignment head and coordinate attention mechanism are incorporated into the model to augment the model’s detection accuracy and recall rate for small targets. Furthermore, to meet the demand for reporting of abnormal situations in unattended environments, an automatic target identification and reporting process has been designed which combines YOLOv5 algorithm with the frame-difference motion detection algorithm. The camera has been tested for compatibility with the current mainstream commercial email platforms. The mean time required for transmitting a single image file via the email platform is less than 10 s, while the mean time for transmitting a short video is less than 60 s. The BP network’s average training loss is 0.015, and the average testing loss is 0.013, which basically meets the precision requirements for gamma adjustment. The improved YOLOv5 algorithm achieved an mAP@0.5 of 91.5% and a recall rate of 85.5%, effectively enhancing the accuracy of small object detection.

Keywords

email transmission / exposure correction / back propagation (BP) neural network / gamma value / YOLOv5

References

[1] LIU X T, HE J F, GAO P, et al. Denoising of 3D Magnetic resonance images based on balanced low-rank tensor and nonlocal self-similarity. Biomedical Signal Processing and Control, 2024, 96: 106588.

[2] XU Z, YANG G Q, ZHANG Y Y. Road target detection algorithm based on improved YOLOv5//2023 IEEE 7th Information Technology and Mechatronics Engineering Conference,September 15-17, 2023, Chongqing, China. New York: IEEE, 2023: 787-791.

[3] RATTHI K I, YOGAMEENA B, PERUMAAL S S. Human height estimation using AI-assisted computer vision for intelligent video surveillance system. Measurement, 2024, 236: 115133.

[4] MAGNO M, TOMBARI F, BRUNELLI D, et al. Multimodal video analysis on self-powered resource-limited wireless smart camera. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2013, 3(2): 223-235.

[5] LIU Q, HIRATSUKA S, GOTO S, et al. A 41mW VGA@30fps quadtree video encoder for video surveillance systems//2007 7th International Conference on ASIC, October 22-25, 2007, Guilin, China. New York: IEEE, 2007: 758-761.

[6] MOSTAFA S A, RAVI S, ASAAD ZEBARI D, et al. A YOLO-based deep learning model for real-time face mask detection via drone surveillance in public spaces. Information Sciences, 2024, 676: 120865.

[7] YANG H M, WANG S, CHEN Y F, et al. Improving power transmission tower state recognition in remote sensing images using cooperative Adaboost-MobileNet. Remote Sensing Letters, 2023, 14(2): 124-134.

[8] BAI Z Y, WANG Y, ZHANG A C, et al. Road surface condition monitoring in extreme weather using a feature-learning enhanced mask–RCNN. Journal of Transportation Engineering, Part B: Pavements, 2024, 150(3): 04024030.

[9] LIU X Y, WANG T, YANG J M, et al. MPQ-YOLO: Ultra low mixed-precision quantization of YOLO for edge devices deployment. Neurocomputing, 2022, 574: 127210.

[10] SUN Q Y, LI P B, HE C T, et al. A lightweight and high-precision passion fruit YOLO detection model for deployment in embedded devices. Sensors, 2024, 24(15): 4942.

[11] WEI X, WEI Y, LU X B. HD-YOLO: Using radius-aware loss function for head detection in top-view fisheye images. Journal of Visual Communication and Image Representation, 2023, 90: 103715.

[12] ABDUSALOMOV A, BARATOV N, KUTLIMURATOV A, et al. An improvement of the fire detection and classification method using YOLOv3 for surveillance systems. Sensors, 2021, 21(19): 6519.

[13] KHAZUKOV K, SHEPELEV V, KARPETA T, et al. Real-time monitoring of traffic parameters. Journal of Big Data, 2020, 7(1): 84.

[14] DARMADI, DONI H N. Traffic counting using YOLO Version-5 (a case study of Jakarta-Cikampek toll road). IOP Conference Series: Earth and Environmental Science, 2024, 1321(1): 012015.

[15] RANI N G, PRIYA N H, AHILAN A, et al. LV-YOLO: logistic vehicle speed detection and counting using deep learning based YOLO network. Signal, Image and Video Processing, 2024, 18(10): 7419-7429.

[16] TIAN Y, YU C Z, XIE F, et al. Research on video detection method of moving target oriented to substation. IOP Conference Series: Earth and Environmental Science, 2021, 804(3): 032011.

[17] GAO Z W, ZHANG N B. Object detection based on RetinaNet and CBAM attention mechanism // International Conference on Internet of Things and Machine Learning (IoTML 2022), December 16-18, 2022, Harbin, China. Society of Photo-Optical Instrumentation Engineers, 2023: 12640.

[18] MA X J, JI K F, XIONG B L, et al. Light-YOLOv4: an edge-device oriented target detection method for remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 10808-10820.

[19] ORTIZ R F, LIN W M. Improving performance of simultaneous multithreading CPUs using autonomous control of speculative traces. Microprocessors and Microsystems, 2024, 108: 105073.

[20] PIEDRAHITA CASTILLO D, REGIDOR F M, HIGUERA J B, et al. A new mail system for secure data transmission in cyber physical systems. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 2020, 28(S2): 23-48.

[21] ZHANG X Y, TANG X J, YU L P, et al. Automated camera exposure control for accuracy-enhanced stereo-digital image correlation measurement. Sensors, 2022, 22(24): 9641.

[22] KARAIMER H C, BROWN M S. A software platform for manipulating the camera imaging pipeline//European Conference on Computer Vision, October 11-14, 2016, Amsterdam, The Netherlands. Cham: Springer International Publishing, 2016: 429-444.

[23] AFIFI M, DERPANIS K G, OMMER B, et al. Learning multi-scale photo exposure correction//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 20-25, 2021, Nashville, TN, USA. New York: IEEE, 2021: 9153-9163.

[24] YI X M, ZHOU Y, WU P, et al. U-Net with coordinate attention and VGGNet: a grape image segmentation algorithm based on fusion pyramid pooling and the dual-attention mechanism. Agronomy, 2024, 14(5): 925.

[25] 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, June 20-25, 2021, Nashville, TN, USA. New York: IEEE, 2021: 13708-13717.

[26] WEI C Y, TAN Z, QING Q X, et al. Fast helmet and license plate detection based on lightweight YOLOv5. Sensors, 2023, 23(9): 4335.

[27] TIAN Z T, CUI J Q, JIANG L, et al. Learning context-aware classifier for semantic segmentation//The 37th AAAI Conference on Artificial Intelligence, February 7-14, 2023, Washing. DC, USA. New York: ACM, 2023: 2438-2446.

[28] LI X, WANG W H, WU L J, et al. Generalized focal loss//34th International Conference on Neural Information Processing Systems, December 6-12, 2020, Vancouver, BC, Canada. New York: ACM, 2020: 21002-21012.

[29] ZHAO M, YANG R, HU M, et al. Deep learning-based technique for remote sensing image enhancement using multiscale feature fusion. Sensors, 2024, 24(2): 673-688.

[30] LI J, SUN H C, ZHANG Z Y. A multi-scale-enhanced YOLO-V5 model for detecting small objects in remote sensing image information. Sensors, 2024, 24(13): 4347.

[31] VAN AMERSFOORT J, SMITH L, TEH Y W, et al. Uncertainty estimation using a single deep deterministic neural network//The 37th International Conference on Machine Learning, July 12-18, 2020, Vienna, Austria. New York: ACM, 2020: 9690-9700.