Publications by authors named "Fenmei Wang"
Article Synopsis
- Automatic pest detection using computer vision faces challenges in distinguishing similar pests due to texture and scale similarities.
- A new task called Appearance Similarity Pest Detection (ASPD) is proposed, featuring two metrics: Multi-Texton Histogram (MTH) for texture and Object Relative Size (ORS) for scale.
- The authors introduce a dataset named PestNet-AS and a method called ASP-Det, which employs Pairwise Self-Attention (PSA) and Skip-Calibrated Convolution (SCC) to improve pest classification accuracy and balance size variations.
Specialized pest control for agriculture is a high-priority agricultural issue. There are multiple categories of tiny pests, which pose significant challenges to monitoring. Previous work mainly relied on manual monitoring of pests, which was labor-intensive and time-consuming.
View Article and Find Full Text PDF