Environmental Engineering
用于分拣效率估算的计算机视觉系统
Computer Vision System for Sorting Efficiency EstimationA dual-camera computer-vision system that estimates manual sorting efficiency in non-ferrous scrap recycling by counting input and output materials using YOLO detectors and Kalman-filter tracking. / 一种双摄像头计算机视觉系统，利用YOLO检测器和卡尔曼滤波跟踪技术，通过计数输入和输出材料来估算有色金属废料回收中的人工分拣效率。
- Knowledge type
- 实际应用
- First proposed or discovered
- Proposer
- Turkey Farm member
- Creator
- 农场主
- Last updated
- 2026-11-11 18:07:01
Sub-knowledge points
Dual-camera setup for input/output comparisonIn-plant dataset training (4361 images, four classes)Per-class and hourly efficiency indicatorsSensitivity analysis for error propagation
Higher-order knowledge points
Industry 4.0 recycling line monitoringNon-ferrous scrap recycling refining stageContinuous efficiency measurement
Main parameters and performance indicators
YOLOv11m: Detector architectureKalman-filter tracker: Tracking algorithmLine-crossing counter: Object counting methodmAP@50: Mean Average Precision metricF1-score: Classification performance metric
Open problems
Validation of accuracy against manual reference countsImage-level splitting bias in detector metricsReal output-camera test image availability
Related literature
ranked by community starsAutomatic Estimation of Manual Sorting Efficiency in Non-Ferrous Scrap Recycling Using Dual-Camera Computer Vision and Deep LearningOpen source
Related products and links
YOLO detectorsKalman-filter trackerLine-crossing counter
Creation and modification trail
1 recordsRecord title: Computer Vision System for Sorting Efficiency Estimation.
Node update feedback
review required