Vehicle-type detection tool has many applications in transportation, traffic control, guiding and controlling unmanned vehicles, tolls and road taxes, traffic violations, smuggling detection, etc. In the proposed version, the MobileNet neural network and the YOLO V5 algorithm are integrat...
YOLOv5n-L相比YOLOv5n,在平均精度(mAP@0.5)上提高了1.7%,达到了0.678;同时模型大小从3.8MB减少到了2.3MB,减小了约40%。 YOLOv5n-MB通过使用MBConv,在保持较高精度(mAP@0.5 = 0.670)的同时,模型大小从3.8MB减少到3.2MB。 YOLOv5n-DW使用DWConv,虽然精度略低于YOLOv5n(mAP@0.5 = 0.664),但模型大小更小(...
This paper aims to propose an accurate, efficient and real-time vehicle detection network based on the successful YOLOv5 object detection model. This is done by improving the structure of the model, adding attention mechanism and using an adaptive bounding box regression loss function. Also, ...
This paper presents a robust vehicle detection technique based on Improved You Look Only Once (RVD-YOLOv5) to enhance vehicle detection accuracy. The proposed method works in three phases; in the first phase, the K-means algorithm performs data clustering on datasets to generate the classes of ...
the public UAV aerial dataset VisDrone2019 demonstrate that the proposed algorithm improves the detection accuracy by 9.3% compared to the original YOLOv5 baseline network, showing better detection performance for small objects. For the UCAS_AOD dataset, the proposed algorithm outperforms YOLOv5-s by...
To solve the feature loss caused by the compression of high-resolution images during the normalization stage, an adaptive clipping algorithm based on the You Only Look Once (YOLO) object detection al...
In order to take use the deep learning method for vehicle tracking detection, recognition and counting, this paper proposes a vehicle detection method based on yolov5. This method uses the deep learning technology, takes the running vehicles video as the research object, analysis the target ...
Figure 4. Integrating a small target detection head improves YOLOv5s 2.2.3. Loss Function Optimization The core YOLOv5 model consists of three components: localization loss, confidence loss, and class loss. The computation of confidence and class losses involves the utilization of a binary cross-...
YOLOv5 has emerged as a preferred choice within the scope of ITS due to its balance between detection accuracy and computational efficiency. It introduces several improvements over its predecessors, including better feature extraction through advanced backbone networks and enhanced bounding box regression ...
Additionally, Jupyter Notebook is utilized to evaluate the photos using the obtained inference graph. Colab Pro, equipped with a Tesla 4 GPU and 25 GB of RAM, was used for the training. Yolov5 is the only model not selected from the most recent TensorFlow 2 detection model zoo28. The ...