Cotton boll localization method based on point annotation and multi-scale fusion

Abstract

Cotton is an important source of fiber. The precise and intelligent management of cotton fields is the top priority of cotton production. Many intelligent management methods of cotton fields are inseparable from cotton boll localization, such as automated cotton picking, sustainable boll pest control, boll maturity analysis, and yield estimation. At present, object detection methods are widely used for crop localization. However, object detection methods require relatively expensive bounding box annotations for supervised learning, and some non-object regions are inevitably included in the annotated bounding boxes. The features of these non-object regions may cause misjudgment by the network model. Unlike bounding box annotations, point annotations are less expensive to label and the annotated points are only likely to belong to the object. Considering these advantages of point annotation, a point annotation-based multi-scale cotton boll localization method is proposed, called MCBLNet. It is mainly composed of scene encoding for feature extraction, location decoding for localization prediction and localization map fusion for multi-scale information association. To evaluate the robustness and accuracy of MCBLNet, we conduct experiments on our constructed cotton boll localization (CBL) dataset (300 in-field cotton boll images). Experimental results demonstrate that MCBLNet method improves by 49.4% average precision on CBL dataset compared with typically point-based localization state-of-the-arts. Additionally, MCBLNet method outperforms or at least comparable with common object detection methods.