TempNet: Temporal Attention Towards the Detection of Animal Behaviour in Videos

TL;DR

TempNet is a novel deep learning approach that uses temporal attention and wavelet pre-processing to accurately and efficiently detect animal behaviors in underwater videos, outperforming existing methods.

Contribution

The paper introduces TempNet, a new model with temporal attention and wavelet down-sampling for behavior detection, demonstrating superior accuracy and efficiency over state-of-the-art methods.

Findings

Achieves 80% accuracy and 0.81 precision in behavior detection.

Outperforms baseline methods with 31% higher accuracy.

Processes 4-second video clips in only 38ms.

Abstract

Recent advancements in cabled ocean observatories have increased the quality and prevalence of underwater videos; this data enables the extraction of high-level biologically relevant information such as species' behaviours. Despite this increase in capability, most modern methods for the automatic interpretation of underwater videos focus only on the detection and counting organisms. We propose an efficient computer vision- and deep learning-based method for the detection of biological behaviours in videos. TempNet uses an encoder bridge and residual blocks to maintain model performance with a two-staged, spatial, then temporal, encoder. TempNet also presents temporal attention during spatial encoding as well as Wavelet Down-Sampling pre-processing to improve model accuracy. Although our system is designed for applications to diverse fish behaviours (i.e, is generic), we demonstrate its application to the detection of sablefish (Anoplopoma fimbria) startle events. We compare the proposed approach with a state-of-the-art end-to-end video detection method (ReMotENet) and a hybrid method previously offered exclusively for the detection of sablefish's startle events in videos from an existing dataset. Results show that our novel method comfortably outperforms the comparison baselines in multiple metrics, reaching a per-clip accuracy and precision of 80% and 0.81, respectively. This represents a relative improvement of 31% in accuracy and 27% in precision over the compared methods using this dataset. Our computational pipeline is also highly efficient, as it can process each 4-second video clip in only 38ms. Furthermore, since it does not employ features specific to sablefish startle events, our system can be easily extended to other behaviours in future works.