3D laser scanning strategy based on cascaded deep neural network

A 3D laser scanning strategy based on cascaded deep neural network is proposed for the scanning system converted from 2D Lidar with a pitching motion device. The strategy is aimed at moving target detection and monitoring. Combining the device characteristics, the strategy first proposes a cascaded deep neural network, which inputs 2D point cloud, color image and pitching angle. The outputs are target distance and speed classification. And the cross-entropy loss function of network is modified by using focal loss and uniform distribution to improve the recognition accuracy. Then a pitching range and speed model are proposed to determine pitching motion parameters. Finally, the adaptive scanning is realized by integral separate speed PID. The experimental results show that the accuracies of the improved network target detection box, distance and speed classification are 90.17%, 96.87% and 96.97%, respectively. The average speed error of the improved PID is 0.4239°/s, and the average strategy execution time is 0.1521 s.The range and speed model can effectively reduce the collection of useless information and the deformation of the target point cloud. Conclusively, the experimental of overall scanning strategy show that it can improve target point cloud integrity and density while ensuring the capture of target.

Pneumatic separation system for collected seedlings using subdivided air streams

To adhere to the needs of automated supply of collected seedlings for mechanized grafting and cutting machines for enhancing their operational efficiency,herein,a separation system that uses subdivided air streams to separate the collected seedlings is developed.The separation system comprises a feeder for supplying collected seedlings,a seedling separator that uses subdivided air streams,a picking belt for the separated seedlings,a delivery unit for the separated seedlings,a pneumatic unit,and a control unit.To investigate the complete performance of separation,picking,and delivery of the separation system,several separation experiments were conducted to separate the collected Anthurium seedlings.The results show that the consistency of the moving direction of seedlings floated by subdivided air streams in the separation container and the moving direction of the picking belt have a significant effect on the picking of the separated seedlings by the picking belt.Moreover,the seedling supply timing of the feeder has a significant effect on the stability of the collected seedling separation rate during continuous separation.When this timing is such that the percentage of separated seedlings is 70%,the separation rate of continuous separation operation is 2.24 plant/s(the separation productivity is 8060 plants/h)with 0.12 CV.The operating conditions are 0.5 MPa separation pressure,0.5 s nozzle operation time,and 60 mm seedling thickness in the separation container.Moreover,the staying times of the collected seedlings separated in the separation container are less than 2.5 min.