• siddharth sandbhor
• Saurabh Solkar

The current camera system been installed is not smart to detect the anonymous activities and notify it to the authority The old systems were taking to much time to train the module with the dataset and the system used to analyze the data on the server side this was time consuming process. Proposed system will be made smart by using external hardware and software which will detect anonymous activities in the bus to improve security .System will Use raspberry PCB with installed android things/raspbian operating system in it . using Machine Learning the system will detect anonymous activities .In machine learning, a convolutional neural network (CNN, or ConvNet) is a class of deep, feed-forward artificial neural networks, most commonly applied to analyzing visual imagery. In machine learning the pretrained modules (e.g. mobile net ,inception) will be used in this neural networks. Also the dataset (e.g. coco,imagenet) will be used.

internet of Things, Machine Learning, Convolution Neural Network.

"Smart Camera System Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.379-385, June-2019, Available :http://www.jetir.org/papers/JETIR1906A61.pdf

"Smart Camera System Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp379-385, June-2019, Available at : http://www.jetir.org/papers/JETIR1906A61.pdf