Vehicle and Pedestrian Detection Based on Improved YOLOv4-tiny Model

Ma, Lingzhe; Chen, Yu; Zhang, Jilin

doi:10.1088/1742-6596/1920/1/012034

Cited by 11 publications

(10 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al [31], proposed a YOLOv4-based model for sea surface object detection scheme. Ma et al [32] reported an improved YOLOv4 small algorithm. The simulation results reveal that, when compared to YOLOv4-tiny, the upgraded network structure has a 3.3% higher accuracy and a detection speed of 251 frames per second, which meets the real-time detection criteria.…”

Section: Research Contributionsmentioning

confidence: 99%

Object Classification and Tracking Using Scaled P8 YOLOv4 Lite Model

Shaikh

Chopade

Kharate

2023

Period. Polytech. Elec. Eng. Comp. Sci.

View full text Add to dashboard Cite

One of the most difficult tasks in the area of computer vision is object detection, which combines object categorization and object location within a scene. In terms of object detection, Deep Neural Networks have been recently demonstrated to outperform alternative approaches. The issues related deep learning neural network is its complexity and huge computation, so it is not possible to detect and track the objects in image of high resolution in real time. We proposed scaled YOLOv4 lite model as Single Stage Detector Neural Network for object detection, tracking and it is trained using COCO 2017 dataset. To create the YOLOv4-CSP- P5- P6- P7- P8 networks, the Scaled YOLOv4 applied efficient network scaling strategies. The additional layer in YOLOv4 lite model is added as P8 layer which improves accuracy. Cross-stage-partial (CSP) connections and Mish activation are used in improved network design, such as backbone optimization and Neck (PAN). In the case of YOLOv4, however, it can only be trained once for all resolutions. Width and Height activations have been changed, allowing for faster network training. With YOLOv4 lite model, we used CSPDarkNet-53 model as a backbone. The experimental result show our YOLOv4 lite model can detect and track object up to 28 fps when model run with the video input and has an accuracy of 86.09% when tested on real-time video with resolutions 1920 × 1080 (full HD). AP = 50.81%, AP @50 = 63.6%, and AP @75 = 52.5% for CSPDarkNet-53 model backbone.

show abstract

Section: Research Contributionsmentioning

confidence: 99%

Object Classification and Tracking Using Scaled P8 YOLOv4 Lite Model

Shaikh

Chopade

Kharate

2023

Period. Polytech. Elec. Eng. Comp. Sci.

View full text Add to dashboard Cite

show abstract

“…The YOLOv4-Tiny [5] network has a total of 38 layers in its overall structure, where three residual units are used in the network. In this work, using Leaky Rectified Linear Unit (ReLU) is taken as the activation function, and the classification and regression for the target is modified by two feature layers, using the Feature Pyramids Networks (FPN) [6] With 416 x 416 inputs, the network structure of YOLOv4-Tiny as shown in Fig.…”

Section: Tolov4-tinymentioning

confidence: 99%

Maize pests identification based on improved YOLOv4-Tiny

Hua

Zhang²,

Zhang³

et al. 2023

Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022)

View full text Add to dashboard Cite

Agricultural pest identification occupies a key position in agricultural economy and development. The accurate identification of pests is the premise of agricultural pest control. In recent years, image processing technology and deep learning technology have rapidly developed. Some researches have been applied to the field of insect recognition. Thus, some insect recognition deep learning models with good recognition accuracy and speed have been established. However, there is still much room for improvement when they were applied to the insect monitoring system deployed in the field. Considering the target recognition accuracy and speed, this paper selects the target detection algorithm YOLOv4-Tiny as the base model for insect recognition. The major advances are the attention mechanism and Spatial Pyramidal Pooling (SPP) structure as shown in: applying Convolutional Block Attention Module (CBAM) reduce computation and number of parameters; adopting SPP structure multi-scale pooling of input feature layers which increases the perceptual field and improves the robustness of the model. The experimental results show that the improved YOLOv4-Tiny model can significantly enhance the insect recognition accuracy.

show abstract

“…However, it is not conducive to the detection of small targets because only two prediction branches with 32 times and 16 times of sampling reduction are retained. Therefore, based on comprehensive consideration of detection accuracy and detection speed, YOLO V4-tiny was selected as the basic network for the study [6][7]. It can be seen from Figure 1 that in YOLO V4-tiny, CSPdarknet53_tiny is used as the backbone feature extraction network for early feature extraction.…”

Section: Yolo V4 -Tiny Networkmentioning

confidence: 99%

Automatic detection method of scrap material of scrap automobile based on improved YOLO V4-tiny

Zhou¹,

Chen²,

Chen³

et al. 2023

International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID 2022)

View full text Add to dashboard Cite

Aiming at the problem of low visual recognition accuracy of waste materials (copper, brass, aluminum and plastic) in the scrap automobile industry, A novel YOLO V4-tiny algorithm was proposed by adding Mosaic data enhancement and improving the Efficient Channel Attention (ECA) Attention mechanism to the original feature extraction network, which strengthened the learning ability of the target detection algorithm and made the network focus on effective features. Suppress interference features, enhance the model's attention to useful information, improve the detection ability of the algorithm. The improved network model was trained, verified and tested on the self-made data set. The results show that the algorithm can effectively improve the identification accuracy of scrap materials of scrapped vehicles, and finally improve the mAP (mean Average Precision) of the existing YOLOV4-tiny algorithm from 91.33% to 95.17%.

show abstract

Vehicle and Pedestrian Detection Based on Improved YOLOv4-tiny Model

Cited by 11 publications

References 2 publications

Object Classification and Tracking Using Scaled P8 YOLOv4 Lite Model

Object Classification and Tracking Using Scaled P8 YOLOv4 Lite Model

Maize pests identification based on improved YOLOv4-Tiny

Automatic detection method of scrap material of scrap automobile based on improved YOLO V4-tiny

Contact Info

Product

Resources

About