Evaluation of deep learning architectures for wildlife object detection: A comparative study of ResNet and Inception

TL;DR

This study compares ResNet-101 and Inception v3 deep learning architectures for wildlife object detection, demonstrating high accuracy and mAP, with Inception v3 slightly outperforming ResNet-101 under complex environmental conditions.

Contribution

It provides a comparative analysis of ResNet-101 and Inception v3 for wildlife detection, highlighting their effectiveness and challenges in real-world ecological monitoring.

Findings

Inception v3 achieved 95% accuracy and 0.92 mAP.

ResNet-101 achieved 94% accuracy and 0.91 mAP.

Both models faced challenges with similar species and poor lighting conditions.

Abstract

Wildlife object detection plays a vital role in biodiversity conservation, ecological monitoring, and habitat protection. However, this task is often challenged by environmental variability, visual similarities among species, and intra-class diversity. This study investigates the effectiveness of two individual deep learning architectures ResNet-101 and Inception v3 for wildlife object detection under such complex conditions. The models were trained and evaluated on a wildlife image dataset using a standardized preprocessing approach, which included resizing images to a maximum dimension of 800 pixels, converting them to RGB format, and transforming them into PyTorch tensors. A ratio of 70:30 training and validation split was used for model development. The ResNet-101 model achieved a classification accuracy of 94% and a mean Average Precision (mAP) of 0.91, showing strong performance in extracting deep hierarchical features. The Inception v3 model performed slightly better, attaining a classification accuracy of 95% and a mAP of 0.92, attributed to its efficient multi-scale feature extraction through parallel convolutions. Despite the strong results, both models exhibited challenges when detecting species with similar visual characteristics or those captured under poor lighting and occlusion. Nonetheless, the findings confirm that both ResNet-101 and Inception v3 are effective models for wildlife object detection tasks and provide a reliable foundation for conservation-focused computer vision applications.