Autonomous Vehicle Target Detection With Adaptive Sparse Convolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional target detection methods are inadequate for accurately and timely detecting remote targets in vehicle environments, especially at high speeds, leading to insufficient safety distances and increased driving risks.
Innovation Solution
A target detection method involving rasterization of three-dimensional point clouds into grids, determination of convolution dilation rates based on sparsity, dilation of sparse convolutions, and use of an attention mechanism to extract and weight point cloud features for accurate detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional target detection methods are used, then close targets can be detected, but remote targets cannot be detected accurately and timely
Solution Approach 1:
The patent segments the point cloud space into multiple three-dimensional point cloud grids, allowing different regions (remote and close targets) to be processed independently with appropriate convolution dilation rates, enabling accurate detection of both remote and close targets simultaneously
Solution Approach 2:
The patent dynamically adjusts the convolution dilation rate based on the sparsity of each point cloud grid, allowing the system to adaptively optimize detection parameters for different spatial regions, improving both accuracy and efficiency
2Productivity
If the vehicle travels at high speed, then productivity increases, but safety distance requirement increases
Solution Approach 1:
The patent performs preliminary detection of remote targets using optimized point cloud grid processing before the vehicle reaches critical distances, allowing the system to prepare safety responses in advance, ensuring adequate safety distance is maintained even at high speeds
3Measurement precision
If point cloud grids are processed with high resolution, then detection accuracy improves, but calculation time increases
Solution Approach 1:
The patent applies different convolution dilation rates to different point cloud grids based on their sparsity, allowing high-resolution processing only where needed (in sparse regions) while using coarser processing in dense regions, optimizing the balance between accuracy and calculation time
Data Source
AI summary
The disclosure relates to the technical field of autonomous driving, and specifically provides a target detection method, a computer device, a computer-readable storage medium, and a vehicle, to solve the problem of detecting a target in a timely and accurate manner. For this purpose, the method of the disclosure includes: rasterizing point cloud space of three-dimensional point clouds in a vehicle driving environment to form a plurality of three-dimensional point cloud grids, and using point cloud grids including three-dimensional point clouds as target point cloud grids; determining a convolution dilation rate based on sparsity of the target point cloud grid; dilating a sparse convolution based on the convolution dilation rate; extracting a point cloud grid feature of the target point cloud grid by using a dilated sparse convolution; weighting the point cloud grid feature by using an attention mechanism to obtain a global point cloud feature; and performing target detection based on the global point cloud feature. In this way, both a remote target and a close target can be accurately detected. In addition, using the sparse convolution for detection can reduce the calculation amount and improve the detection efficiency.