Framework for environment perception: Ensemble method for vision-based scene understanding algorithms in agriculture

The safe and reliable operation of autonomous agricultural vehicles requires an advanced environment perception system. An important component of perception systems is vision-based algorithms for detecting objects and other structures in the fields. This paper presents an ensemble method for combining outputs of three scene understanding tasks: semantic segmentation, object detection and anomaly detection in the agricultural context. The proposed framework uses an object detector to detect seven agriculture-specific classes. The anomaly detector detects all other objects that do not belong to these classes. In addition, the segmentation map of the field is utilized to provide additional information if the objects are located inside or outside the field area. The detections of different algorithms are combined at inference time, and the proposed ensemble method is independent of underlying algorithms. The results show that combining object detection with anomaly detection can increase the number of detected objects in agricultural scene images.

Automated summary

This paper presents an ensemble method that combines semantic segmentation, object detection, and anomaly detection tasks in agricultural scenes. The proposed method detects agriculture-specific classes using an object detector and detects other objects using an anomaly detector. The segmentation map is utilized to provide additional information about the location of objects. The results show that combining object detection with anomaly detection increases the number of detected objects in agricultural scene images.