Manisha Chate

Bio: Manisha Chate is an academic researcher from Amity University. The author has contributed to research in topics: Convolutional neural network & Deep learning. The author has co-authored 3 publications.

Vehicle Detection Using Faster Recurrent Convolution Neural Network

Abstract: Extension of fast R-CNN (Recurrent Convolution Neural Network) [1] and Recurrent-CNN [2] is Faster Recurrent CNN detection techniques. All these three strategies use convolutional neural networks (CNN). The distinction between them is the way to select the regions to work and the way those regions are categorised. Recurrent CNN and fast R-CNN used algorithm proposed region as a pre-processing step before running CNN. Algorithms are usually technical proposals such as Borders [3] or Selective Search [4] boxes, which are independent of CNN. Fast Recurrent CNN, the use of these systems becomes bottleneck process with relevance to CNN’s operation. Fast R-CNN solves this downside by applying the projected mechanism to use the region and then CNN. An RPN is a fully convex network that predicts object boundaries and object scores at each location simultaneously.

Application of Recurrent Convolution Neural Network for Vehicle Detection

Abstract: Object tracking and monitoring is used for detection purpose. This research is found since last two decades. However, the scope is there for further improvement. Cur-rent deep neural network model is found suitable in this area exclusively. We examine the problem of vehicle discov-ery by the deep learning method. In addition, we have shown that the use of deep features extracted from a pre-formed network produces a more efficient and ac-curate means of monitoring. Fast Recurrent CNN, the use of these systems becomes bottleneck process with relevance to CNN's operation. Fast R-CNN solves this downside by applying the projected mechanism to use the region and then CNN. An RPN is a fully convex network that predicts object boundaries and object scores at each location simultaneous-ly.

Heavy Vehicle Detection Using Fine-Tuned Deep Learning

Abstract: Heavy vehicles develop technical snag and traffic jam on streets. Accidents between heavy vehicle and road users, for example, pedestrians often result in severe injuries of the weaker street users. The highway safety and traffic jams can be secured with detection of heavy and overloaded vehicles on the highway to facilitate light motor vehicles like cars, scooters. A model for heavy vehicle detection using fine-tuned based on deep learning is proposed to deal with entangled transportation scene. This model comprises two parts, vehicle detection model and vehicle fine-grained detection. This step provides data for the next classification model. Experiments show that vehicle’s make and model can be recognized from transportation images effectively by using our method. Experimental results demonstrate that the proposed detection system performs accurately with other simple and complex scenarios in detecting heavy vehicles in comparison with past vehicle detection systems.