Laser & Optoelectronics Progress, Volume. 61, Issue 4, 0437005(2024)
Coal and Gangue Recognition Method Based on Dual-Channel Pseudocolor Image by Lidar
Fig. 1. Example maps of production environment and industrial camera data. (a) Data collection environment; (b) data acquisition by industrial camera
Fig. 2. Schematic diagram of acquisition system
Fig. 3. Point cloud images. (a) Distance point cloud; (b) intensity point cloud
Fig. 4. Image of coal and gangue strength. (a) Coal; (b) gangue
Fig. 5. Example of distance point cloud
Fig. 6. Process of image preprocessing
Fig. 7. Background denoising. (a) Before removal; (b) after removal
Fig. 8. Point cloud image generation process. (a) Original point cloud map; (b) vertical view of point cloud; (c) real point cloud projection; (d) two dimension intensity pixel image
Fig. 9. Dual channel pseudo color image generation process. (a) Intensity point cloud; (b) distance point cloud; (c) dual channel pseudo color image
Fig. 10. DenseNet-121 network structure
Fig. 11. Dual channel pseudo color image used in the experiment. (a) Coal; (b) gangue
Fig. 12. Training accuracy and training loss curves. (a) (d) DenseNet-40; (b) (e) DenseNet-121; (c) (f) DenseNet-201
|
|
|
|
Get Citation
Copy Citation Text
Yan Wang, Jichuan Xing, Yaozhi Wang. Coal and Gangue Recognition Method Based on Dual-Channel Pseudocolor Image by Lidar[J]. Laser & Optoelectronics Progress, 2024, 61(4): 0437005
Category: Digital Image Processing
Received: Dec. 1, 2022
Accepted: Feb. 6, 2023
Published Online: Feb. 26, 2024
The Author Email: Xing Jichuan (michaelhsing@bit.edu.cn)