A Lightweight Vehicle-Pedestrian Detection Algorithm Based on Attention Mechanism in Traffic Scenarios

Zhang, Yong; Zhou, Aibo; Zhao, Fang; Wu, Haixiao

doi:10.3390/s22218480

Cited by 12 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, this section proposes a multitask model based on object detection and road segmentation in unstructured road scenes. The proposed model consists of multiple object detection [48] and road semantic segmentation models, enabling simultaneous completion of multiple visual perception tasks. The model provides comprehensive and accurate visual information for automotive driving systems, thereby enhancing perception and system safety.…”

Section: Multitask Model and Network Structurementioning

confidence: 99%

Research on multitask model of object detection and road segmentation in unstructured road scenes

Gao,

Zhao,

Zhang

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

With the rapid development of artificial intelligence and computer vision technology, autonomous driving technology has become a hot area of concern. The driving scenarios of autonomous vehicles can be divided into structured scenarios and unstructured scenarios.Compared with structured scenes, unstructured road scenes lack the constraints of lane lines and traffic rules, and the safety awareness of traffic participants is weaker. Therefore, there are new and higher requirements for the environment perception tasks of autonomous vehicles in unstructured road scenes. The current research rarely integrates the target detection and road segmentation to achieve the simultaneous processing of target detection and road segmentation of autonomous vehicle in unstructured road scenes. Aiming at the above issues, a multitask model for object detection and road segmentation in unstructured road scenes is proposed. Through the sharing and fusion of the object detection model and road segmentation model, multitask model can complete the tasks of multi-object detection and road segmentation in unstructured road scenes while inputting a picture. Firstly, MobileNetV2 is used to replace the backbone network of YOLOv5, and multi-scale feature fusion is used to realize the information exchange layer between different features.Subsequently, a road segmentation model was designed based on the DeepLabV3+ algorithm.Its main feature is that it uses MobileNetV2 as the backbone network and combines the binary classification focus Loss function for network optimization. Then, we fused the object detection algorithm and road segmentation algorithm based on the shared MobileNetV2 network to obtain a multitask model and trained it on both the public dataset and the self-built dataset NJFU. The training results demonstrate that the multitask model significantly enhances the algorithm's execution speed by approximately 10 FPS while maintaining the accuracy of object detection and road segmentation. Finally, we conducted validation of the multitask model on an actual vehicle.

show abstract

Section: Multitask Model and Network Structurementioning

confidence: 99%

Research on multitask model of object detection and road segmentation in unstructured road scenes

Gao,

Zhao,

Zhang

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The application of Attention mechanisms ( Zhang et al., 2022 ) enables the neural network to focus on important features and suppress unnecessary features. This paper uses the Convolutional Block Attention Module ( Woo et al., 2018 ).…”

Section: Related Workmentioning

confidence: 99%

A lightweight method for maize seed defects identification based on Convolutional Block Attention Module

Li,

Chen,

Jing

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

Maize is widely cultivated and planted all over the world, which is one of the main food resources. Accurately identifying the defect of maize seeds is of great significance in both food safety and agricultural production. In recent years, methods based on deep learning have performed well in image processing, but their potential in the identification of maize seed defects has not been fully realized. Therefore, in this paper, a lightweight and effective network for maize seed defect identification is proposed. In the proposed network, the Convolutional Block Attention Module (CBAM) was integrated into the pretrained MobileNetv3 network for extracting important features in the channel and spatial domain. In this way, the network can be focused on useful feature information, and making it easier to converge. To verify the effectiveness of the proposed network, a total of 12784 images was collected, and 7 defect types were defined. Compared with other popular pretrained models, the proposed network converges with the least number of iterations and achieves the true positive rate is 93.14% and the false positive rate is 1.14%.

show abstract

“…It encompasses three main components, including environmental perception [ 4 ], path planning [ 5 ], and tracking control [ 6 ]. The first part relies on various sensors to detect the external environment and input this information into the autonomous vehicle system [ 7 , 8 , 9 ], thereby establishing the foundation for subsequent planning and control [ 10 ]. The objective of planning is to determine the most optimized path for intelligent vehicles using appropriate algorithms [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

Research on Path Planning and Path Tracking Control of Autonomous Vehicles Based on Improved APF and SMC

Zhang,

Liu,

Gao

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Path planning and tracking control is an essential part of autonomous vehicle research. In terms of path planning, the artificial potential field (APF) algorithm has attracted much attention due to its completeness. However, it has many limitations, such as local minima, unreachable targets, and inadequate safety. This study proposes an improved APF algorithm that addresses these issues. Firstly, a repulsion field action area is designed to consider the velocity of the nearest obstacle. Secondly, a road repulsion field is introduced to ensure the safety of the vehicle while driving. Thirdly, the distance factor between the target point and the virtual sub-target point is established to facilitate smooth driving and parking. Fourthly, a velocity repulsion field is created to avoid collisions. Finally, these repulsive fields are merged to derive a new formula, which facilitates the planning of a route that aligns with the structured road. After path planning, a cubic B-spline path optimization method is proposed to optimize the path obtained using the improved APF algorithm. In terms of path tracking, an improved sliding mode controller is designed. This controller integrates lateral and heading errors, improves the sliding mode function, and enhances the accuracy of path tracking. The MATLAB platform is used to verify the effectiveness of the improved APF algorithm. The results demonstrate that it effectively plans a path that considers car kinematics, resulting in smaller and more continuous heading angles and curvatures compared with general APF planning. In a tracking control experiment conducted on the Carsim–Simulink platform, the lateral error of the vehicle is controlled within 0.06 m at both high and low speeds, and the yaw angle error is controlled within 0.3 rad. These results validate the traceability of the improved APF method proposed in this study and the high tracking accuracy of the controller.

show abstract

A Lightweight Vehicle-Pedestrian Detection Algorithm Based on Attention Mechanism in Traffic Scenarios

Cited by 12 publications

References 36 publications

Research on multitask model of object detection and road segmentation in unstructured road scenes

Research on multitask model of object detection and road segmentation in unstructured road scenes

A lightweight method for maize seed defects identification based on Convolutional Block Attention Module

Research on Path Planning and Path Tracking Control of Autonomous Vehicles Based on Improved APF and SMC

Contact Info

Product

Resources

About