This paper explores the field of Object Detection and the advancements in the same. We delve deep into different neural network-based object detection models, with emphasis on their application and address some of the challenges faced in this field. Object detection has a growing importance in fields like agriculture, manufacturing, security surveillance, autonomous vehicles etc. This paper compares different models: Convolution Neural Networks (CNN) Region-based Convolutional Neural Networks (R-CNN), Fast R-CNN, Faster R-CNNs, You Only Look Once (YOLO) and Single Shot Detectors (SSD) based on robustness, adaptability, and real-time processing capabilities. We see which models are suited for real-time applications and which are suited for feature extraction. Despite significant progress,, there are still challenges that are faced in this field.