Multi-Objective Detection of Traffic Scenes Based on Improved SSD

Xia, 华夏 Hua; Xinqing, 王新晴 Wang; Dong, 王东 Wang; Zhaoye, 马昭烨 Ma; Faming, 邵发明 Shao

doi:10.3788/aos201838.1215003

Cited by 8 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the classification of scrap steel into light as shown in Figure 1a, medium as shown in Figure 1b, heavy types as shown in Figure 1c, oily as shown in Figure 1d, and confined as shown in Figure 1e The traditional detection algorithm types are the V-J (Viola and Jones) detection algorithm [10], the HOG (Histogram of Oriented Gradients) and SVM (Support Vector Machine) detection algorithm [11], the DPM (Deformable Part-Based Model) algorithm [12], etc. However, there are still many problems with traditional target detection methods because sliding windows bring a large number of redundant windows, which consume a lot of time, and because the robustness and generalization are too poor due to the use of manually extracted features [13], so the traditional target detection algorithms are not suitable for use in industrialized scenarios.…”

Section: Introductionmentioning

confidence: 99%

Large Span Sizes and Irregular Shapes Target Detection Methods Using Variable Convolution-Improved YOLOv8

Gao,

Liu,

Chui

et al. 2024

Sensors

View full text Add to dashboard Cite

In this work, an object detection method using variable convolution-improved YOLOv8 is proposed to solve the problem of low accuracy and low efficiency in detecting spanning and irregularly shaped samples. Aiming at the problems of the irregular shape of a target, the low resolution of labeling frames, dense distribution, and the ease of overlap, a deformable convolution module is added to the original backbone network. This allows the model to deal flexibly with the problem of the insufficient perceptual field of the target corresponding to the detection point, and the situations of leakage and misdetection can be effectively improved. In order to solve the issue that small target detection is susceptible to image background and noise interference, the Sim-AM (simple parameter-free attention mechanism) module is added to the backbone network of YOLOv8, which enhances the attention to the underlying features and, thus, improves the detection accuracy of the model. More importantly, the Sim-AM module does not need to add parameters to the original network, which reduces the computation of the model. To address the problem of complex model structures that can lead to slower detection, the spatial pyramid pooling of the backbone network is replaced with focal modulation networks, which greatly simplifies the computation process. The experimental validation was carried out on the scrap steel dataset containing a large number of targets of multiple shapes and sizes. The results showed that the improved YOLOv8 network model improves the AP (average precision) by 2.1%, the mAP (mean average precision value) by 0.8%, and reduces the FPS (frames per second) by 5.4, which meets the performance requirements of real-time industrial inspection.

show abstract