A detailed methodology of object detection in a smart city setting has been illustrated in this chapter. The presented methodology focuses on intelligent uses of machine learning and deep learning algorithms for effective extraction of desired ROI from a challenging backdrop. This chapter encompasses a Convolutional Neural Network (CNN) based architecture and a Faster RCNN based approach and holistic comparisons are being made between the results obtained from the different approaches. The problem that has been tried to address through this work, is the lack of robust algorithms that can detect occluded objects effectively, that may commonly occur in a smart city. So, the primary focus of this work is to devise a methodology that can detect even minute objects camouflaged in city crowd, which are prevalent in smart cities across India. This work is believed to be beneficial in various sectors, even in military, to help them with reconnaissance task. Further the proposed methodology is equipped with an alarm system that warns against plausible security breach and intrusion. This mechanism enhances security of a smart city using IOT techniques. The entire methodology described in the chapter can be deployed without use of any additional hardware. Overall the proposed framework is robust, effective and viable for multi facet uses in the future and can be effectively deployed in large distributed systems across smart cites of India.