Abstract
In recent years, the application of deep learning technology in the field of food engineering has developed rapidly. As an essential food raw material and processing target, the number of kernels per maize plant is a critical indicator for assessing crop growth and predicting yield. To address the challenges of frequent target ID switching, high falling speed, and the limited accuracy of traditional methods in practical production scenarios for maize kernel falling count, this study designs and implements a real-time kernel falling counting system based on a Convolutional Neural Network (CNN). The system captures dynamic video streams of kernel falling using a high-speed camera and innovatively integrates the YOLOv8 object detection framework with the ByteTrack multi-object tracking algorithm to establish an efficient and accurate kernel trajectory tracking and counting model. Experimental results demonstrate that the system achieves a tracking and counting accuracy of up to 99% under complex falling conditions, effectively overcoming counting errors caused by high-speed motion and object occlusion, and significantly enhancing robustness. This system combines high intelligence with precision, providing reliable technical support for automated quality monitoring and yield estimation in food processing production lines, and holds substantial application value and prospects for widespread adoption.