Customized Smart Object Detection: Statistics of detected objects using IoT

• Published in: 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS) pp. 1397 - 1405
• Main Authors: Lalitha, V. Lakshmi, Raju, S. Hrushikesava, Sonti, Vijaya Krishna, Mohan, V. Murali
• Format: Conference Proceeding
• Language: English
• Published: IEEE 25.03.2021
• Subjects: and Customized training; Cameras; image detection; Intelligence camera; Internet of Things; Monitoring; Object detection; Object recognition; Objects; Real-time systems; Sensors; Training; YOLO
• DOI: 10.1109/ICAIS50930.2021.9395913

Nowadays, detecting an object through a camera requires training over a few samples similar to the particular kind. The proposed system makes training over different kinds of samples and allows noting the statistics of each kind of object. The proposed system consists of a camera embedded with this computational intelligence that will work as expected. The camera when programmed using specific intelligence leads to identify the different objects on which it is trained. This system can detect multiple objects in the space monitored by the programmed camera. The statistics include the count of each category object, time frames, day-wise details, and other details that are important for analysis. This system could be useful in many real-time applications where the count of objects is needed as well as other applications where specific detail is considered important. The specific sensors are embedded along with a suitable programmed environment that helps to monitor the specific environment. Based on the reports, the next step is to be taken for a healthier environment. The feeding and training of objects are user-friendly and are customized. Hence, a large kind of real-time application is suitable for processing.