Improved Deep Learning Architecture For Depth Estimation

Improved depth map estimation in Stereo Vision

In this paper, we present a new approach for dense stereo matching which is mainly oriented towards the recovery of depth map of an observed scene. The extraction of depth information from the disparity map is well understood, while the correspondence problem is still subject to errors. In our approach, we propose optimizing correlation based technique by detecting and rejecting mismatched poin...

Improved Interpretability and Generalisation for Deep Learning

Improved Dropout for Shallow and Deep Learning

Dropout has been witnessed with great success in training deep neural networks by independently zeroing out the outputs of neurons at random. It has also received a surge of interest for shallow learning, e.g., logistic regression. However, the independent sampling for dropout could be suboptimal for the sake of convergence. In this paper, we propose to use multinomial sampling for dropout, i.e...

Meteonowcasting using Deep Learning Architecture

The area of deep learning has enjoyed a resurgence on its peak, in almost every field of interest. Weather forecasting is a complicated and one of the most challenging tasks that includes observing and processing huge amount of data. The present paper proposes an effort to apply deep learning approach for the prediction of weather parameters such as temperature, pressure and humidity of a parti...

Deep Learning for Laser Based Odometry Estimation

In this paper we take advantage of recent advances in deep learning techniques focused on image classification to estimate transforms between consecutive point clouds. A standard technique for feature learning is to use convolutional neural networks. Leveraging this technique can help with one of the biggest challenges in robotic motion planning, real time odometry. Sensors have advanced in rec...