Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny

Cheng, Rao; He, Xiaowei; Zheng, Zhonglong; Wang, Zhentao

doi:10.3390/app11083652

Cited by 50 publications

(13 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The loss function mainly includes three parts: position error, confidence error, and classification error, 23 which are defined as follows…”

Section: Vehicle Detection Light-weighted Networkmentioning

confidence: 99%

“…After obtaining the prediction results on these two scales, the non-maximum suppression (NMS) algorithm is applied to get the final results. 22 The loss function mainly includes three parts: position error, confidence error, and classification error, 23 which are defined as follows…”

Section: Vehicle Detection Network Yolov3-tinymentioning

confidence: 99%

“…The large anchor box is used to predict large objects and the small anchor box is used to predict small objects. Therefore, the three candidate boxes [46, 83], [65,131], and [104,1989] are used to predict bounding box on the scale of 13 3 13, the three candidate boxes [18,48], [26,68], and [36,50] are used to predict bounding box on the scale of 26 3 26, and the rest three candidate boxes [9,23], [13,33], and [24,35] are used to predict small bounding box on the scale of 52 3 52. Since the results of Kmeans clustering depend on the selection of initial clustering center, six clustering experiments were done in this article, as shown in Table 2.…”

Section: Optimization Of Vehicle Detection Networkmentioning

confidence: 99%

See 2 more Smart Citations

Light-weighted vehicle detection network based on improved YOLOv3-tiny

Guo

et al. 2022

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

Vehicle detection is one of the most challenging research works on environment perception for intelligent vehicle. The commonly used object detection network is too large and can only be realized in real-time on a high-performance server. Based on YOLOv3-tiny, the feature extraction was realized using light-weighted networks such as DarkNet-19 and ResNet-18 to improve accuracy. The K-means algorithm was used to cluster nine anchor boxes to achieve multi-scale prediction, especially for small targets. For automotive applicable scenarios, the proposed vehicle detection network was executed in an embedded device. The KITTI data sets were trained and tested. Experimental results show that the average accuracy is improved by 14.09% compared with the traditional YOLOv3-tiny, reaching 93.66%, and can reach 13 fps on the embedded device.

show abstract

“…The loss function mainly includes three parts: position error, confidence error, and classification error, 23 which are defined as follows…”

Section: Vehicle Detection Light-weighted Networkmentioning

confidence: 99%

Section: Vehicle Detection Network Yolov3-tinymentioning

confidence: 99%

Section: Optimization Of Vehicle Detection Networkmentioning

confidence: 99%

See 1 more Smart Citation

Light-weighted vehicle detection network based on improved YOLOv3-tiny

Guo

et al. 2022

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

show abstract

“…To solve the problem of efficiency and storage, researchers have designed lightweight networks to improve the inference speed. For example, the YOLOv3-Tiny [ 51 ] network launched for high parameters and inference speed is a simplified version of the YOLOv3 network. Iandola et al [ 52 ] proposed SqueezeNet.…”

Section: Related Workmentioning

confidence: 99%

A Lightweight CNN Model Based on GhostNet

Wang

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The existing deep learning models have problems such as large weight parameters and slow inference speed of equipment. In practical applications such as fire detection, they often cannot be deployed on equipment with limited resources due to the huge amount of parameters and low efficiency. In response to this problem, this paper proposes a lightweight smoke detection model based on the convolutional attention mechanism module. The model is based on the YOLOv5 lightweight framework. The backbone network draws on the GhostNet design idea, replaces the CSP structure of the FPN and head layers with the GhostBottleNeck module, adds a convolutional attention mechanism module to the backbone network layer, and uses the CIoU loss function to improve the regression accuracy. Using YOLOv5s as the benchmark model, the parameter amount of the proposed lightweight neural network model is 2.75 M, and the floating-point calculation amount is 2.56 G, which is much lower than the parameter amount and calculation amount of the benchmark model. Tested on the public fire dataset, compared with the traditional deep learning algorithm, the model proposed in the paper has better detection performance and the detection speed is significantly better than the benchmark model. Tested under the unquantized simulator, the speed of the proposed model to detect a single picture is 60 ms, which can meet the requirements of real-time engineering applications.

show abstract

“…CIoU regression loss is employed to improve MSE regression loss [43], and the improved loss function is more suitable for detecting small objects in traffic scenes. CIoU inherits the advantages of Generalized Intersection Over Union (GIoU) [44] and Distance-IoU (DIoU) [45], which not only considers the distance and overlap ratio but also considers the scale and the aspect ratio between the prediction box and the ground truth box so that it can carry out the bounding box regression better [43]. It consists of three parts: the first is loss CIoU , which represents regression loss; The second part is loss obj , which represents confidence loss.…”

Section: Loss Functionmentioning

confidence: 99%

Small Object Detection in Traffic Scenes Based on YOLO-MXANet

Cheng

Zheng

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

In terms of small objects in traffic scenes, general object detection algorithms have low detection accuracy, high model complexity, and slow detection speed. To solve the above problems, an improved algorithm (named YOLO-MXANet) is proposed in this paper. Complete-Intersection over Union (CIoU) is utilized to improve loss function for promoting the positioning accuracy of the small object. In order to reduce the complexity of the model, we present a lightweight yet powerful backbone network (named SA-MobileNeXt) that incorporates channel and spatial attention. Our approach can extract expressive features more effectively by applying the Shuffle Channel and Spatial Attention (SCSA) module into the SandGlass Block (SGBlock) module while increasing the parameters by a small number. In addition, the data enhancement method combining Mosaic and Mixup is employed to improve the robustness of the training model. The Multi-scale Feature Enhancement Fusion (MFEF) network is proposed to fuse the extracted features better. In addition, the SiLU activation function is utilized to optimize the Convolution-Batchnorm-Leaky ReLU (CBL) module and the SGBlock module to accelerate the convergence of the model. The ablation experiments on the KITTI dataset show that each improved method is effective. The improved algorithm reduces the complexity and detection speed of the model while improving the object detection accuracy. The comparative experiments on the KITTY dataset and CCTSDB dataset with other algorithms show that our algorithm also has certain advantages.

show abstract

Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny

Cited by 50 publications

References 30 publications

Light-weighted vehicle detection network based on improved YOLOv3-tiny

Light-weighted vehicle detection network based on improved YOLOv3-tiny

A Lightweight CNN Model Based on GhostNet

Small Object Detection in Traffic Scenes Based on YOLO-MXANet

Contact Info

Product

Resources

About