Intelligent System Utilizing HOG and CNN for Thermal Image-Based Detection of Wild Animals in Nocturnal Periods for Vehicle Safety

Animal Vehicle Collision, commonly called roadkill, is an emerging threat to drivers and wild animals, increasing fatalities every year. Currently, prevalent methods using visible light cameras are efficient for animal detection in daylight time. This paper focuses on locating wildlife close roads during nocturnal hours by utilizing thermographic obtained images, thus enhancing vehicle safety. In particular, it proposes intelligent system nighttime that combines the technique of Histogram Oriented Gradients (HOG) with a Convolutional Neural Network (CNN). The proposed benchmarked against variety CNN’s like basic CNN VGG16-based also machine learning algorithms such as Support Vector Machine (SVM), Random Forest (RF), Decision Tree Algorithm (DT), Linear Regression (LR), Gaussian Naïve Bayes (GNB). was tested set real-world data acquired thermal camera move city San Antonio, TX, USA includes images deer. Obtained results exhibit HOG-CNN combination achieved approximately 91% correct accuracy deer roadsides, while outperformed rest algorithms.