Understanding the Purpose of Object Detection, Models to Detect Objects, Application Use and Benefits

Abstract

Object detection is the latest technology which is used to identify objects and instances of objects in ana image or a video. It is the computer vision technique which is useful in determining the instances of objects in the image and also to identify their locations. The advantage of this technique is that it gives accurate location of the objects and also helps to label them in the image. Object detection contributes a lot in major fields like crowd detection at a particular place, self-driving cars, helps to identify theft by video surveillance etc. Object detection is also used to identify the face recognition, pedestrian recognition which ensures safety on road, also used in image retrieval etc. There are many models which are used in object detection process to simplify the process and gives accurate and efficient results. This paper will discuss the various approaches which are used along with object detection process to enhance the quality of results it will provide.

A Survey on Various Congestion Control Techniques in Wireless Sensor Networks

“…Their simulation and analysis results show that this new protocol outperforms existing performance protocols in terms of performance, packet delivery, and package loss. According to V. E. Narawade et al [16], congestion degrades WSN performance because it wastes energy, reduces performance, and causes a significant loss of information. Several methods for avoiding congestion for transmitting data packets without data loss can be used to avoid this.…”

MDAS_DBRCC: Data Backup and Recovery Technique in Cloud Computing for Education Industry

“…Cloud computing's rapid growth in the educational research and technological organizations has resulted in considerable benefits in terms of cooperation, efficiency, and scalability. [3].…”

Microstrip Patch Antenna Parameter Optimization Prediction Model using Machine Learning Techniques

“…J. Nan et al, presents the whole fractal antenna structure and the notch structure of the MIMO antenna have both been optimally designed using the proposed model, and their Sparameters are in good agreement with the requirements and design goals. The DBN-ELM method outperforms other common modelling approaches on the same training samples (with an assessed root mean square error of 11.87 percent for the fractal antenna and 3.56 percent for the MIMO antenna) [3]. N. Kurniawati et al, find that three estimators have a small mean absolute error (MAE) for gain, while two have a small mean squared error (MSE).…”

“…Higher frequency range-18GHz to 100 GHz, the satellite and radar communication is mostly lie in this frequency range. The current technology doesn't meet the constraints of the 5G communication so need some enhancement in the conventional wireless communication optimization algorithm and the physical antenna structure [3].…”