YOLOv7-RAR for Urban Vehicle Detection

Abstract

Aiming at the problems of high missed detection rates of the YOLOv7 algorithm for vehicle detection on urban roads, weak perception of small targets in perspective, and insufficient feature extraction, the YOLOv7-RAR recognition algorithm is proposed. The algorithm is improved from the following three directions based on YOLOv7. Firstly, in view of the insufficient nonlinear feature fusion of the original backbone network, the Res3Unit structure is used to reconstruct the backbone network of YOLOv7 to improve the ability of the network model architecture to obtain more nonlinear features. Secondly, in view of the problem that there are many interference backgrounds in urban roads and that the original network is weak in positioning targets such as vehicles, a plug-and-play hybrid attention mechanism module, ACmix, is added after the SPPCSPC layer of the backbone network to enhance the network’s attention to vehicles and reduce the interference of other targets. Finally, aiming at the problem that the receptive field of the original network Narrows, with the deepening of the network model, leads to a high miss rate of small targets, the Gaussian receptive field scheme used in the RFLA (Gaussian-receptive-field-based label assignment) module is used at the connection between the feature fusion area and the detection head to improve the receptive field of the network model for small objects in the image. Combining the three improvement measures, the first letter of the name of each improvement measure is selected, and the improved algorithm is named the YOLOv7-RAR algorithm. Experiments show that on urban roads with crowded vehicles and different weather patterns, the average detection accuracy of the YOLOv7-RAR algorithm reaches 95.1%, which is 2.4% higher than that of the original algorithm; the AP50:90 performance is 12.6% higher than that of the original algorithm. The running speed of the YOLOv7-RAR algorithm reaches 96 FPS, which meets the real-time requirements of vehicle detection; hence, the algorithm can be better applied to vehicle detection.

Lightweight multi-target detection algorithm for unmanned aerial vehicle aerial imagery

“…Although the YOLOv7-tiny algorithm is widely used in target detection tasks, the YOLOv7-tiny algorithm has a weak ability to extract small target features and cannot complete traffic target detection tasks effectively 20 . In traffic images, relatively high-level features contain rich semantic information, but due to multi-level convolutional operation, the position information of small targets is severely lost, whereas low-level features contain rich position information and detailed information of small targets 21 . To extract the small target semantic feature information in the feature map, we proposed the new feature enhancement module named enhance feature fusion module (EFFM) (as shown in Fig.…”

STAE‐YOLO: Intelligent detection algorithm for risk management of construction machinery intrusion on transmission lines based on visual perception

“…The backbone comprises a convolutional structure and an aggregation network ELAN. Extracted features are then directed to the global feature enhancement ST module and the SPPCSPC [28] module. The PAFPN [29] structure is employed to extract input information of varying sizes for fusion.…”

Study on the detection technology for inner-wall outer surface defects of the automotive ABS brake master cylinder based on BM-YOLOv8

“…As a result, they necessitate extensive hardware resources for both training and inferencing. The You Only Look Once (YOLO) algorithm series [14][15][16][17][18][19][20] are one-stage detection methodologies, requiring a singular feature extraction phase for complete target detection, and are lauded for their superior efficiency. Wang et al [14] proposed the YOLOv7 model, which integrates an efficient long-range attention network, and a cascade scaling approach.…”

“…However, its intrinsic limitation is the large downsampling multiplier, reducing its capability to discern deep features in tiny targets, which predisposes it to potential detection lapses. For this purpose, Zhang et al [16] harnessed the Acmix attention mechanism to enhance the feature extraction capability of the YOLOv7 model, particularly for minute targets. However, the Acmix attention mechanism makes flexible allocation determination difficult.…”