Efficient and Lightweight Framework for Real-Time Ore Image Segmentation Based on Deep Learning
Guodong Sun, Delong Huang, Le Cheng, Junjie Jia, Chenyun Xiong, Yang Zhang
Abstract
Image segmentation approaches have been utilized to determine the particle size distribution of crushed ores in the past decades. It is not possible to deploy large and high-powered computing equipment due to the complex working environment, so existing algorithms are difficult to apply in practical engineering. This article presents a novel efficient and lightweight framework for ore image segmentation to discern full and independent ores. First, a lightweight backbone is introduced for feature extraction while reducing computational complexity. Then, we propose a compact pyramid network to process the data obtained from the backbone to reduce unnecessary semantic information and computation. Finally, an optimized detection head is proposed to obtain the feature to maintain accuracy. Extensive experimental results demonstrate the effectiveness of our method, which achieves 40 frames per second on our new ore image dataset with a very small model size. Meanwhile, our method maintains a high level of accuracy—67.68% in AP50box and 46.73% in AP50mask—compared with state-of-the-art approaches.