Improving Object Detection for Time-Lapse Imagery Using Temporal Features in Wildlife Monitoring

TL;DR

This paper introduces a method that enhances object detection in wildlife time-lapse images by incorporating temporal features, significantly improving accuracy and reducing false positives in animal monitoring.

Contribution

The paper presents a novel approach that integrates spatio-temporal features into object detection for time-lapse imagery, boosting performance over traditional single-frame methods.

Findings

Achieved a 24% improvement in mean average precision (mAP) over baseline.

Effectively reduces stationary false positives in wildlife images.

Applicable to various wildlife monitoring scenarios using time-lapse imaging.

Abstract

Monitoring animal populations is crucial for assessing the health of ecosystems. Traditional methods, which require extensive fieldwork, are increasingly being supplemented by time-lapse camera-trap imagery combined with an automatic analysis of the image data. The latter usually involves some object detector aimed at detecting relevant targets (commonly animals) in each image, followed by some postprocessing to gather activity and population data. In this paper, we show that the performance of an object detector in a single frame of a time-lapse sequence can be improved by including spatio-temporal features from the prior frames. We propose a method that leverages temporal information by integrating two additional spatial feature channels which capture stationary and non-stationary elements of the scene and consequently improve scene understanding and reduce the number of stationary false positives. The proposed technique achieves a significant improvement of 24\% in mean average precision (mAP@0.05:0.95) over the baseline (temporal feature-free, single frame) object detector on a large dataset of breeding tropical seabirds. We envisage our method will be widely applicable to other wildlife monitoring applications that use time-lapse imaging.