Animal Detection in Man-made Environments
This addresses a domain-specific safety issue for human-inhabited areas, but the approach is incremental as it builds on existing deep learning techniques.
The paper tackled the problem of detecting animals in man-made environments for security and road safety, finding that detectors fail to generalize from natural habitat training images, and proposed a solution using semi-automated synthetic data generation.
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.