Towards Toxic and Narcotic Medication Detection with Rotated Object Detector

TL;DR

This paper presents a rotated YOLO-based object detection method tailored for identifying toxic and narcotic medications with arbitrary orientations, achieving high accuracy and efficiency for densely arranged drugs.

Contribution

It introduces a flexible annotation scheme and a mask-mapping non-maximum suppression method for improved detection of arbitrarily oriented medication objects.

Findings

Mean average precision reaches 0.811

Inference time is less than 300ms

Rotated YOLO detectors outperform standard methods in dense drug detection

Abstract

Recent years have witnessed the advancement of deep learning vision technologies and applications in the medical industry. Intelligent devices for special medication management are in great need of, which requires more precise detection algorithms to identify the specifications and locations. In this work, YOLO (You only look once) based object detectors are tailored for toxic and narcotic medications detection tasks. Specifically, a more flexible annotation with rotated degree ranging from $0^\circ$ to $90^\circ$ and a mask-mapping-based non-maximum suppression method are proposed to achieve a feasible and efficient medication detector aiming at arbitrarily oriented bounding boxes. Extensive experiments demonstrate that the rotated YOLO detectors are more suitable for identifying densely arranged drugs. The best shot mean average precision of the proposed network reaches 0.811 while the inference time is less than 300ms.