Multi-level Approach for Detection and Identification of Camouflaged Lifeform: A comprehensive detailing of identifying camouflaged Lifeforms

Camouflaged object detection and Identification (CODnI) in natural environment, especially involving lifeform, pose inherent challenges due to computational complexity. Leveraging the insights from human vision, a multilevel CODnI approach has been presented to improve both the detection accuracy and the computational efficiency, addressing the challenges of high miss rates, high type-1 and type-II errors and low confidence. Further, the proposed machine vision approach has been augmented with a physics-based feature using infrared (IR) band in addition to red, green and blue (RGB) data. Performance of the model has been evaluated for a camouflaged natural environment image dataset that have been used extensively over last few years. Presented technique found to achieve significantly high detection rate (miss rate 2.63% only), F1 score of 0.97 and 0.95 confidence level (p value 0.05).