Object Detection And Recognition Using Tensorflow

Abstract

Creating the accurate machine learning models capable of localizing and identifying multiple objects in a single image remain a core challenge in computer vision. The TensorFlow Object Detection API is open source framework built on top of TensorFlow that makes it is easy to construct, train and deploy object detection models. Efficient and accurate objects detection has been an important topic in the advancement in computer vision systems with the advent of deep learning techniques, the accuracy for object detection has increased drastically, the paper aims to incorporate state of the-art technique for object detection with the goal of achieving high accuracy with a real-time performance. major challenge in many of the object detection systems is the dependence on other computer vision techniques for helping the deep learning-based approaches, which leads to slow and non-optimal performance in this paper we use completely deep learning-based approach to solve the problem of object detection in an end-to-end fashion. The network is train on the most challenging publicly available dataset (PASCAL VOC), on which the object detection challenge is conducted annually. The resulting system is fast and accurate, thus adding those applications which require object detection. The aim of this study is to explore the modern open source-based solutions for object detection in sports: in this case for detecting football players. The model is tested as a dataset consisting of images extract from video footage of two football Matches Following hypotheses were examine: 1) Pre trained model will not work on data without fine tuning. 2) Fine tuned model will work reasonably well on given data. 3) Fine tuned model will have problem with occlusion and player pictures against the rear wall. 4) Using more variable training data will improve the results on new images.