Detecting Small Scale Pedestrians and Anthropomorphic Negative Samples Based on Light-Field Imaging

Zhao, Yufeng; Shi, Fan; Zhao, Meng; Zhang, Wenzhe; Chen, Shengyong

doi:10.1109/access.2020.2999694

Cited by 4 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experiments using the MS COCO [22], [23], [49], KAIST [50], [51], and Campus Video Datasets demonstrate the YOLO-ACN's ability to improve detection accuracy and speed of small targets and occluded objects over conventional and related models. Training and deployment of models are performed using a server equipped with Intel XeonE5-26031.8GH CPU and NVIDIA Tesla K40 12GB GPU card with a 2880 CUDA parallel processing core.…”

Section: Experimental Analysismentioning

confidence: 94%

“…The twostage detectors are represented by R-CNN [12]- [14], and the one-stage detectors are represented by SSD (single shot multibox detector) [15], [16] and YOLO [17]- [19]. These milestone algorithms have achieved good detection results on large datasets, e.g., PASCAL VOC [20], [21] and MS COCO [22], [23]. As a representative one-stage object detection algorithm, YOLOv3 has been widely adopted because of the high speed and accuracy [24], and it directly uses a more powerful network to extract the features and generate regression BBox of the objects.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

YOLO-ACN: Focusing on Small Target and Occluded Object Detection

et al. 2020

IEEE Access

101

View full text Add to dashboard Cite

Section: Experimental Analysismentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

YOLO-ACN: Focusing on Small Target and Occluded Object Detection

et al. 2020

IEEE Access

101

View full text Add to dashboard Cite

“…In this experiment, three mixed datasets are used to evaluate the PF_YOLOv4. The datasets are: MS COCO [36], [37], INRIA [38] and self-made datasets.…”

Section: Experiments a Dataset And Implementation Detailsmentioning

confidence: 99%

PFYOLOv4: An Improved Small Object Pedestrian Detection Algorithm

Zhuang

Lai

et al. 2023

IEEE Access

View full text Add to dashboard Cite

With the development of deep convolutional neural networks, the effect of pedestrian detection has been rapidly improved. However, there are still many problems in small target pedestrian detection, for example noise (such as light) interference, target occlusion, and low detection accuracy. In order to solve the above problems, based on YOLOv4 algorithm, this paper proposes an improved small target pedestrian detection algorithm named PF_YOLOv4. The algorithm is improved in three aspects on the basis of the YOLOv4 algorithm: firstly, a soft thresholding module is added to the residual structure of the backbone network to perform noise reduction process on interference factors, such as light to enhance the robustness of the algorithm; secondly, the depthwise separable convolution replaces the traditional convolution in the YOLOv4 residual structure, to reduce the number of network model parameters; finally, the Convolutional Block Attention Module (CBAM) is added after the output feature map of the backbone network to enhance of the network feature expression. Experimental results show that the PF_YOLOv4 algorithm outperforms most of the state-of-the-art algorithms in detecting small target pedestrians. The mean Average Precision (mAP) of the PF_YOLOv4 algorithm is 2.35% higher than that of the YOLOv4 algorithm and 9.67% higher than that of the YOLOv3 algorithm, while the detection speed is slightly higher than that of YOLOv4 algorithm.INDEX TERMS Small target pedestrian detection, soft thresholding, depthwise separable convolution, convolutional block attention module I. INRTODUCTION

show abstract

“…In recent years, deep learning technology has played an important role in pedestrian detection tasks. The two-stage detection and one-stage detection algorithms has the advantage in precision [8,9] and speed respectively. In ZHAO B., et al [10], YOLOv3 is improved by adding prediction layer, integrating attention mechanism and building anchor mask.…”

Section: Related Workmentioning

confidence: 99%

Pedestrian Detection Algorithm Based on Improved YOLOv3_tiny

Yang

Kang

2021

Proceedings of 2021 Chinese Intelligent Automation Conference

View full text Add to dashboard Cite

In view of the low detection accuracy of YOLOv3_tiny algorithm on small pedestrian target, a pedestrian detection method to improve YOLOv3_tiny is proposed. Firstly, the head and shoulder of the pedestrian are taken as the detection object. The K-means++ algorithm is used to improve the k-means algorithm and cluster the data set to get the anchor frame with higher accuracy. Secondly, add a target prediction layer with a resolution of 52 × 52 to the multi-scale prediction section, which improves the detection accuracy of the small target. In addition, the backbone structure of YOLOv3_tiny is light-weighted, which further compresses the model memory and reduces the deployment burden of the model while maintaining accuracy. A comparative experiment is conducted on the self-made pedestrian dataset which tags the head and shoulder. The results show that the recall of the improved algorithm is 0.8743, which is 11.78% higher than that of the original algorithm; The average accuracy is 77.69%, which is better than the classical algorithms, such as SSD, fast RCNN and Yolo v3; the model size is 26M, and the test time of single image is 0.0789s, which can achieve efficient and real-time detection.

show abstract

Detecting Small Scale Pedestrians and Anthropomorphic Negative Samples Based on Light-Field Imaging

Cited by 4 publications

References 50 publications

YOLO-ACN: Focusing on Small Target and Occluded Object Detection

YOLO-ACN: Focusing on Small Target and Occluded Object Detection

PFYOLOv4: An Improved Small Object Pedestrian Detection Algorithm

Pedestrian Detection Algorithm Based on Improved YOLOv3_tiny

Contact Info

Product

Resources

About