Ensemble Learning Model for Object Detection in Image and Videos

Object detection is a very difficult task in many applications. Presently many authors are trying to develop new research applications to find the objects in Images and videos. In images, static objects are identified and in videos, dynamic objects are identified which are called moving objects. Deep Learning and Artificial intelligence playa major role in finding the objects in Images and also in Videos. So many existing methods are developed for the detection of objects from various sources. In real-time applications, obj ect detection can be used to find malicious objects also. In this paper, an ensemble model is developed to find the accurate objects from the given inputs. The ensemble model is the combination of YOLOV3 (You Only Look Once) and a Convolutional neural network (CNN). The dataset used in this paper is COCO-2017 collected from online sources. The performance of the proposed approach is analyzed by comparing it with the several existing approaches.