Convolutional Neural Networks (CNN) have performed extremely well for many image analysis tasks. However, supervised training of deep CNN architectures requires huge amounts of labelled data which is unavailable for light field images. In this paper, we leverage on synthetic light field images and propose a two stream CNN network that learns to estimate the disparities of multiple correlated neighbourhood pixels from their Epipolar Plane Images (EPI). Since the EPIs are unrelated except at their intersection, a two stream network is proposed to learn convolution weights individually for the EPIs and then combine the outputs of the two streams for disparity estimation. The CNN estimated disparity map is then refined using the central RGB light field image as a prior in a variational technique. We also propose a new real world dataset comprising light field images of 19 objects captured with the Lytro Illum camera in outdoor scenes and their corresponding 3D pointclouds, as ground truth, captured with the 3dMD scanner. This dataset will be made public to allow more precise 3D pointcloud level comparison of algorithms in the future which is currently not possible. Experiments on the synthetic and real world datasets show that our algorithm outperforms existing state-of-the-art for depth estimation from light field images.

First-person videos have unique characteristics such as heavy egocentric motion, strong preceding events, salient transitional activities and post-event impacts. Action recognition methods designed for third person videos may not optimally represent actions captured by first-person videos. We propose a method to represent the high level dynamics of sub-events in first-person videos by dynamically pooling features of sub-intervals of time series using a temporal feature pooling function. The sub-event dynamics are then temporally aligned to make a new series. To keep track of how the sub-event dynamics evolve over time, we recursively employ the Fast Fourier Transform on a pyramidal temporal structure. The Fourier coefficients of the segment define the overall video representation. We perform experiments on two existing benchmark first-person video datasets which have been captured in a controlled environment. Addressing this gap, we introduce a new dataset collected from YouTube which has a larger number of classes and a greater diversity of capture conditions thereby more closely depicting real-world challenges in first-person video analysis. We compare our method to state-of-the-art first person and generic video recognition algorithms. Our method consistently outperforms the nearest competitors by 10.3%, 3.3% and 11.7% respectively on the three datasets.

Deep learning based methods have achieved unprecedented success in solving several computer vision problems involving RGB images. However, this level of success is yet to be seen on RGB-D images owing to two major challenges in this domain: training data deficiency and multi-modality input dissimilarity. We present an RGB-D object recognition framework that addresses these two key challenges by effectively embedding depth and point cloud data into the RGB domain. We employ a convolutional neural network (CNN) pre-trained on RGB data as a feature extractor for both color and depth channels and propose a rich coarse-to-fine feature representation scheme, coined Hypercube Pyramid, that is able to capture discriminatory information at different levels of detail. Finally, we present a novel fusion scheme to combine the Hypercube Pyramid features with the activations of fully connected neurons to construct a compact representation prior to classification. By employing Extreme Learning Machines (ELM) as non-linear classifiers, we show that the proposed method outperforms ten state-of-the-art algorithms for several tasks in terms of recognition accuracy on the benchmark Washington RGB-D and 2D3D object datasets by a large margin (upto 50% reduction in error rate).