A5073376225- Image Enhancement Techniques
- Advanced Neural Network Applications
- Advanced Sensor Technologies Research
- Advanced machining processes and optimization
- Advanced Vision and Imaging
- Advanced Image Processing Techniques
- Soil Moisture and Remote Sensing
- Iterative Learning Control Systems
- Autonomous Vehicle Technology and Safety
- Advanced Machining and Optimization Techniques
- 3D Shape Modeling and Analysis
- Remote Sensing and LiDAR Applications
- Advanced Algorithms and Applications
- Advanced Computational Techniques and Applications
- Robotics and Sensor-Based Localization
Shanghai Polytechnic University
2022-2024
China Coal Technology and Engineering Group Corp (China)
2024
LiDAR has become a vital sensor for autonomous driving scene understanding. To meet the accuracy and speed of point clouds semantic segmentation, an efficient model ACPNet is proposed in this paper. In feature extraction stage, backbone constructed with asymmetric convolutions, so skeleton square convolution kernel enhanced, which leads to greater robustness target rotation. Moreover, contextual enhancement module designed extract richer features. During training, global scaling translation...
Fusing LiDAR point cloud and camera image for 3D object detection in autonomous driving has emerged as a captivating research avenue. The core challenge of multimodal fusion is how to seamlessly fuse with 2D image. Although current approaches exhibit promising results, they often rely solely on at either the data level, feature or there still room improvement utilization information. We present an advanced effective framework called EPAWFusion fusing both level level. model consists three...
Abstract The measurement of cutting temperature is very important in monitoring the manufacturing process and greatly impacts tool wear workpiece surface quality. Milling particularly difficult due to high-speed rotation. This paper uses an intelligent wireless passive tool-holder system for milling sensing, with a resolution 0.25°C, range 0~700°C, update speed 10 Hz. Thermocouple pre-embedded machined groove near edge on flank face tool, signal acquisition circuits transmission module are...
China is a large agricultural country, and in the process of production, it very important to make accurate prediction soil moisture. To address problems local minimization slow convergence traditional BP (back propagation) neural network process, this paper combines LSTM (long short-term memory) Elman with model, proposes method based on for moisture prediction. A proposed. The model was developed, Xilinguole grassland Inner Mongolia predicted experimented. results show that accuracy higher...
High-level computer vision tasks often necessitate large-scale, high-quality depth images. However, real-world images are unsuitable for direct application in experimental studies due to their inherent noise and presence of holes. Consequently, image restoration becomes imperative. Large-scale hole repair proves ineffective the face realistic complex degraded scenes. To address this issue, our research introduces fast Fourier convolution a Multi-Scale Attention mechanism into an unsupervised...