Classification of Smoking and Calling using Deep Learning
This work provides a practical solution for classifying specific human behaviors (smoking and calling), potentially useful for monitoring or safety applications, though the impact is limited by the small, biased sample.
This paper addresses the classification of smoking and calling behaviors using a deep learning pipeline. By modifying a pre-trained Inception V3 model and incorporating brightness enhancement, the authors achieved high accuracy on a dataset, despite using small, biased samples.
Since 2014, very deep convolutional neural networks have been proposed and become the must-have weapon for champions in all kinds of competition. In this report, a pipeline is introduced to perform the classification of smoking and calling by modifying the pretrained inception V3. Brightness enhancing based on deep learning is implemented to improve the classification of this classification task along with other useful training tricks. Based on the quality and quantity results, it can be concluded that this pipeline with small biased samples is practical and useful with high accuracy.