Song Chunyi

TL;DR: In this article, a multi-target tracking method based on millimeter-wave radar is proposed, which comprises acquiring point cloud data by millimeter wave radar, clustering the point cloud to distinguish the echo signals of different targets, and estimating the state information of multiple observed targets according to a clustering result so as to track the multiple targets.

TL;DR: In this paper, a millimeter wave radar and visual processing combined mode is adopted to complete target detection and recognition tasks, by means of a deep learning neural network technology, the object positioning time is shortened, and the recognition accuracy is improved.

TL;DR: In this paper, a nuclear support vector machine target classification method based on millimeter-wave radar point cloud features is proposed, and the method comprises the steps: firstly carrying out the preprocessing of original radar point clouds data, and removing point clouds outside a radar detection region; and clustering the target point clouds into one class through a clustering algorithm so asto eliminate noise point clouds; then constructing a feature vector composed of 11 features in combination with the point clouds features of the target, and performing training and testing by adoptinga kernel support vector classifier, thereby realizing

TL;DR: In this paper, a laser radar and vision fused perception method based on a lightweight convolutional neural network was proposed, and the average correctrate was ensured, running time of the network under processing of different lightweight methods and different compressed perception methods was obtained, and a test result was obtained.

TL;DR: In this article, a millimeter-wave radar and camera combined calibration method based on an LM algorithm is proposed, and the method comprises the steps: firstly fixing the positions of the millimeter wave radar and a camera, and measuring the relative position relation between the mmWave radar and the camera; turning on a camera to acquire data, and calibrating the internal reference of the camera by adopting a camera internal reference calibration method; then simultaneously turning on the mmwave radar, and placing a calibration object for data acquisition; fusing the acquired data, using an LM-based