A Lightweight Pedestrian Detection Engine with Two-Stage Low-Complexity Detection Network and Adaptive Region Focusing Technique

Que, Luying; Zhang, Teng; Guo, Hongtao; Jia, Conghan; Gong, Yuchuan; Chang, Liang; Zhou, Jun

doi:10.3390/s21175851

Cited by 4 publications

(6 citation statements)

References 38 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The feature maps with a single scale utilize three prior boxes, and the corresponding relationship between prior boxes and feature maps with different scales is as follows. In detail, the 32-fold downsampled feature maps use the following three prior boxes: [(116,90); (159,198); (373,326)]; the 16-fold downsampled feature maps apply the following three prior boxes: [ (30,61); (62,45); (59,119)]; the 8-fold downsampled feature maps employ the following three prior boxes: [ (10,13); (16,30); (33,23)]. Large feature maps with small receptive fields are very sensitive to small-scale objects, so small prior boxes are selected.…”

Section: Yolov3 Baseline Algorithmmentioning

confidence: 99%

“…At present, many scholars have applied general object detection algorithms to the traffic field. Que Luying et al [13] proposed a lightweight pedestrian detection engine with a two-stage low-complexity detection network and adaptive region focusing technique, which not only reduced the computational complexity but also maintained sufficient detection accuracy. Yang Xiaoting et al [14] proposed a novel scale-sensitive feature reassembly network (SSNet) for pedestrian detection in road scenes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Small Object Detection in Traffic Scenes Based on YOLO-MXANet

Cheng

Zheng

et al. 2021

Sensors

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

Section: Yolov3 Baseline Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Small Object Detection in Traffic Scenes Based on YOLO-MXANet

Cheng

Zheng

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…In recent years, target detection algorithms have performed well among many detection algorithms. Target detection methods are mainly divided into two categories: traditional target detection and deep learning-based target detection [1][2][3]. Traditional target detection algorithms include six key steps: preprocessing, window sliding, feature extraction, feature selection, feature classification, and post-processing.…”

Section: Introductionmentioning

confidence: 99%

A Pedestrian Detection Algorithm Based on Improved YOLOv7-tiny

2024

JSSH

View full text Add to dashboard Cite

With the widespread development of embedded device applications based on deep learning, pedestrian detection using deep learning often requires the use of complex and large neural networks. However, these networks have a large memory footprint, which makes them difficult to deploy on embedded devices, and are computationally intensive, which makes it difficult to guarantee the speed of operation on embedded devices. To address these issues, a lightweight network, YOLO-Micro, is proposed in this paper. The model reduces the complexity of the model by replacing the original module in YOLOv7-tiny with the G-ELAN module proposed in this paper. Meanwhile, the attention mechanism and the activation function were introduced and replaced to enhance the feature extraction capability of the model. Finally, the model was successfully deployed to Android mobile. Experimental results on the PASCAL VOC Pedestrian dataset show that the inference speed of YOLO-Micro is 20.8% faster than the original model, and the mAP is improved from 77.95% to 79.42% of the original model.

show abstract

“…Kamil Roszyk et al adopted a method for low-latency multispectral pedestrian detection in autonomous driving by YOLOv4 [ 16 ]. Luying Que et al proposed a lightweight pedestrian detection engine of a two-stage low-complexity detection network and adaptive region focusing technique [ 17 ]. Yang Liu et al used a thermal infrared vehicle and pedestrian detection method in complex scenes [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

YOLOv5-AC: Attention Mechanism-Based Lightweight YOLOv5 for Track Pedestrian Detection

Yan

Liu

et al. 2022

Sensors

View full text Add to dashboard Cite

In response to the dangerous behavior of pedestrians roaming freely on unsupervised train tracks, the real-time detection of pedestrians is urgently required to ensure the safety of trains and people. Aiming to improve the low accuracy of railway pedestrian detection, the high missed-detection rate of target pedestrians, and the poor retention of non-redundant boxes, YOLOv5 is adopted as the baseline to improve the effectiveness of pedestrian detection. First of all, L1 regularization is deployed before the BN layer, and the layers with smaller influence factors are removed through sparse training to achieve the effect of model pruning. In the next moment, the context extraction module is applied to the feature extraction network, and the input features are fully extracted using receptive fields of different sizes. In addition, both the context attention module CxAM and the content attention module CnAM are added to the FPN part to correct the target position deviation in the process of feature extraction so that the accuracy of detection can be improved. What is more, DIoU_NMS is employed to replace NMS as the prediction frame screening algorithm to improve the problem of detection target loss in the case of high target coincidence. Experimental results show that compared with YOLOv5, the AP of our YOLOv5-AC model for pedestrians is 95.14%, the recall is 94.22%, and the counting frame rate is 63.1 FPS. Among them, AP and recall increased by 3.78% and 3.92%, respectively, while the detection speed increased by 57.8%. The experimental results verify that our YOLOv5-AC is an effective and accurate method for pedestrian detection in railways.

show abstract

A Lightweight Pedestrian Detection Engine with Two-Stage Low-Complexity Detection Network and Adaptive Region Focusing Technique

Cited by 4 publications

References 38 publications

Small Object Detection in Traffic Scenes Based on YOLO-MXANet

Small Object Detection in Traffic Scenes Based on YOLO-MXANet

A Pedestrian Detection Algorithm Based on Improved YOLOv7-tiny

YOLOv5-AC: Attention Mechanism-Based Lightweight YOLOv5 for Track Pedestrian Detection

Contact Info

Product

Resources

About