An Efficient MLP-based Point-guided Segmentation Network for Ore Images with Ambiguous Boundary
Preprint
Abstract
The precise segmentation of ore images is critical to the successful execution of the beneficiation process. Due to the homogeneous appearance of the ores, which leads to low contrast and unclear boundaries, accurate segmentation becomes challenging, and recognition becomes problematic. This paper proposes a lightweight framework based on Multi-Layer Perceptron (MLP), which focuses on solving the problem of edge burring. Specifically, we introduce a lightweight backbone better suited for efficiently extracting low-level features. Besides, we design a feature pyramid network consisting of two MLP structures that balance local and global information thus enhancing detection accuracy. Furthermore, we propose a novel loss function that guides the prediction points to match the instance edge points to achieve clear object boundaries. We have conducted extensive experiments to validate the efficacy of our proposed method. Our approach achieves a remarkable processing speed of over 27 frames per second (FPS) with a model size of only 73 MB. Moreover, our method delivers a consistently high level of accuracy, with impressive performance scores of 60.4 and 48.9 in~$AP_{50}^{box}$ and~$AP_{50}^{mask}$ respectively, as compared to the currently available state-of-the-art techniques, when tested on the ore image dataset. The source code will be released at \url{https://github.com/MVME-HBUT/ORENEXT}.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation Based on Visual Foundation ModelIEEE Transactions on Geoscience and Remote Sensing, 2024
- Feature disentanglement in one-stage object detectionPattern Recognition, 2023
- Faster OreFSDet: A lightweight and effective few-shot object detector for ore imagesPattern Recognition, 2023
- Visual Fault Detection of Multiscale Key Components in Freight TrainsIEEE Transactions on Industrial Informatics, 2022
- A Novel Particle Size Detection System Based on RGB-Laser Fusion Segmentation With Feature Dual-Recalibration for Blast Furnace MaterialsIEEE Transactions on Industrial Electronics, 2022
- A Boundary Consistency-Aware Multitask Learning Framework for Joint Activity Segmentation and Recognition With Wearable SensorsIEEE Transactions on Industrial Informatics, 2022
- Deep Learning Based Mineral Image Classification Combined With Visual Attention MechanismIEEE Access, 2021
- A Unified Light Framework for Real-Time Fault Detection of Freight Train ImagesIEEE Transactions on Industrial Informatics, 2021
- Object Detection Based on Multi-Layer Convolution Feature Fusion and Online Hard Example MiningIEEE Access, 2018
- Ore image segmentation by learning image and shape featuresPattern Recognition Letters, 2009