Animal Detection in Man-made Environments

TL;DR

This paper explores deep learning methods for detecting animals in human environments, highlighting challenges in generalization and proposing synthetic data generation for improved domain adaptation.

Contribution

It introduces a semi-automated synthetic data approach to enhance animal detection in man-made environments, addressing transfer learning limitations.

Findings

Detectors struggle to generalize from natural habitats to man-made settings.

Transfer learning insights reveal domain adaptation challenges.

Synthetic data improves detection performance in deployment scenarios.

Abstract

Automatic detection of animals that have strayed into human inhabited areas has important security and road safety applications. This paper attempts to solve this problem using deep learning techniques from a variety of computer vision fields including object detection, tracking, segmentation and edge detection. Several interesting insights into transfer learning are elicited while adapting models trained on benchmark datasets for real world deployment. Empirical evidence is presented to demonstrate the inability of detectors to generalize from training images of animals in their natural habitats to deployment scenarios of man-made environments. A solution is also proposed using semi-automated synthetic data generation for domain specific training. Code and data used in the experiments are made available to facilitate further work in this domain.