Identification of Growing Points of Cotton Main Stem Based on Convolutional Neural Network

Wang, Chun‐Shan; He, Siqi; Wu, Haiyuan; Teng, Guifa; Zhao, Chunjiang; Li, Jiuxi

doi:10.1109/access.2020.3038396

Cited by 6 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…YOLO2 algorithm gathers several parts of target detection into a deep neural network. Firstly, an image is divided into S×S grids [6] . If the center of a target falls in this grid, this grid is responsible for predicting the target, and each grid is also responsible for B guard boxes.…”

Section: Tiny Yolov2 Realisationmentioning

confidence: 99%

A Design Method for Controlling the Safe Distance of Convolution Image Recognition Based on FPGA

Zhao

Wei

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

This is an FPGA-based image recognition system. It is built on the FPGA-SOC platform, which uses less power and operates more quickly. This method can be used to remind people inside to maintain a safe distance to stop the coronavirus from spreading. The system can ensure a high accuracy rate and identification speed. At the same time, the system detects the safe distance and issues pertinent prompts according to the training of the private data set. Finally, the system’s implementation is appropriate for tiny IoT devices with extremely low power consumption. The system is implemented by utilizing a custom CPU on an FPGA. The RISC-V architecture used in the self-developed CPU allows for 32-bit embedded CPU performance and operating effectiveness at the expense of an 8-bit CPU. An HD camera and an infrared camera that work together are put on it. The upgraded Tiny YOLO2 algorithm in the CPU can help the infrared camera process the HD camera’s data and perform recognition and judgments. Finally, it is possible to implement data collection based on 720p resolution, which precisely determines whether the direct distance between individuals is a safe distance and then sends the appropriate reminders. Its power usage is 1.3 W. It can address the issue of preventing epidemics and the security risks brought on by a large population density in public areas.

show abstract

Section: Tiny Yolov2 Realisationmentioning

confidence: 99%