Infrared road object detection algorithm based on spatial depth channel attention network and improved YOLOv8

Abstract

Aiming at the problems of low detection accuracy and large model size of existing object detection algorithms applied to complex road scenes, an improved you only look once version 8 (YOLOv8) object detection algorithm for infrared images, F-YOLOv8, is proposed. First, a spatial-to-depth network replaces the traditional backbone network’s strided convolution or pooling layer. At the same time, it combines with the channel attention mechanism so that the neural network focuses on the channels with large weight values to better extract low-resolution image feature information; then an improved feature pyramid network of lightweight bidirectional feature pyramid network (L-BiFPN) is proposed, which can efficiently fuse features of different scales. In addition, a loss function of insertion of union based on the minimum point distance (MPDIoU) is introduced for bounding box regression, which obtains faster convergence speed and more accurate regression results. Experimental results on the FLIR dataset show that the improved algorithm can accurately detect infrared road targets in real time with 3% and 2.2% enhancement in mean average precision at 50% IoU (mAP50) and mean average precision at 50%–95% IoU (mAP50-95), respectively, and 38.1%, 37.3% and 16.9% reduction in the number of model parameters, the model weight, and floating-point operations per second (FLOPs), respectively. To further demonstrate the detection capability of the improved algorithm, it is tested on the public dataset PASCAL VOC, and the results show that F-YOLO has excellent generalized detection performance.

Keywords

A

References

[1] ZhaoM, LiW, LiL, et al.. Single-frame infrared small-target detection: a survey. IEEE geoscience and remote sensing magazine, 2022, 10(2): 87-119[J]

[2] CaoY, GuanD, WuY, et al.. Box-level segmentation supervised deep neural networks for accurate and real-time multispectral pedestrian detection. ISPRS journal of photogrammetry and remote sensing, 2019, 150: 70-79[J]

[3] XueT, ZhangZ, MaW, et al.. Nighttime pedestrian and vehicle detection based on a fast saliency and multifeature fusion algorithm for infrared images. IEEE transactions on intelligent transportation systems, 2022, 23(9): 16741-16751[J]

[4] ZhouJ, ZhangB, YuanX, et al.. YOLO-CIR: the network based on YOLO and ConvNeXt for infrared object detection. Infrared physics & technology, 2023, 131104703[J]

[5] LiR, ShenY. YOLOSR-IST: a deep learning method for small target detection in infrared remote sensing images based on super-resolution and YOLO. Signal processing, 2023, 208108962[J]

[6] DongX, YanS, DuanC. A lightweight vehicles detection network model based on YOLOv5. Engineering applications of artificial intelligence, 2022, 113104914[J]

[7] WangA J, YuanJ L, ZhuY J. Drum roller surface defect detection algorithm based on improved YOLOv8s. Journal of Zhejiang University (Engineering Edition), 2024, 58(02): 370-380[J]

[8] JinX, XieY, WeiX S, et al.. Delving deep into spatial pooling for squeeze-and-excitation networks. Pattern recognition, 2022, 121108159[J]

[9] ChenX, WuH, HanB, et al.. Orientation-aware ship detection via a rotation feature decoupling supported deep learning approach. Engineering applications of artificial intelligence, 2023, 125106686[J]

[10] SHI C, ZHENG X, ZHAO Z, et al. LSKF-YOLO: large selective kernel feature fusion network for power tower detection in high-resolution satellite remote sensing images[J]. IEEE transactions on geoscience and remote sensing, 2024, 62.

[11] XuC E, DongZ, ZhongS Y, et al.. Fusion network for small target detection based on YOLO and attention mechanism. Optoelectronics letters, 2024, 20(06): 372-378[J]

[12] DongX H, LiS X, ZhangJ X. YOLOV5s object detection based on Sim SPPF hybrid pooling. Optoelectronics letters, 2024, 20(06): 367-371[J]

[13] BieM, LiuY, LiG, et al.. Real-time vehicle detection algorithm based on a lightweight you-only-look-once (YOLOv5n-L) approach. Expert systems with applications, 2023, 213119108[J]

[14] YangW, WuJ, ZhangJ, et al.. Deformable convolution and coordinate attention for fast cattle detection. Computers and electronics in agriculture, 2023, 211108006[J]

[15] EveringhamM, Van GoolL, WilliamsC K I, et al.. The pascal visual object classes (VOC) challenge. International journal of computer vision, 2010, 88: 303-338[J]

[16] GuemasE, RoutierB, Ghelfenstein-FerreiraT, et al.. Automatic patient-level recognition of four Plasmodium species on thin blood smear by a real-time detection transformer (RT-DETR) object detection algorithm: a proof-of-concept and evaluation. Microbiology spectrum, 2024, 122e01440-23[J]

RIGHTS & PERMISSIONS

Tianjin University of Technology