Learn More
We propose a novel deep architecture, SegNet, for semantic pixel wise image labelling 1. SegNet has several attractive properties; (i) it only requires forward evaluation of a fully learnt function to obtain smooth label predictions, (ii) with increasing depth, a larger context is considered for pixel labelling which improves accuracy, and (iii) it is easy(More)
We introduce the Imperial College London and National University of Ireland Maynooth (ICL-NUIM) dataset for the evaluation of visual odometry, 3D reconstruction and SLAM algorithms that typically use RGB-D data. We present a collection of handheld RGB-D camera sequences within synthetically generated environments. RGB-D sequences with perfect ground truth(More)
Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted the need for enormous quantity of supervised data — performance increases in proportion to the amount of data used.(More)
Ever more robust, accurate and detailed mapping using visual sensing has proven to be an enabling factor for mobile robots across a wide variety of applications. For the next level of robot intelligence and intuitive user interaction, maps need to extend beyond geometry and appearance — they need to contain semantics. We address this challenge by(More)
An event camera is a silicon retina which outputs not a sequence of video frames like a standard camera, but a stream of asynchronous spikes, each with pixel location, sign and precise timing, indicating when individual pixels record a threshold log intensity change (positive or negative). By encoding only image change, it offers the potential to transmit(More)
We describe a new spatio-temporal video autoencoder, based on a classic spatial image autoencoder and a novel nested temporal autoencoder. The temporal en-coder is represented by a differentiable visual memory composed of convolutional long short-term memory (LSTM) cells that integrate changes over time. Here we target motion changes and use as temporal(More)
We introduce SceneNet RGB-D, expanding the previous work of SceneNet to enable large scale photorealistic rendering of indoor scene trajectories. It provides pixel-perfect ground truth for scene understanding problems such as semantic segmentation, instance segmentation, and object detection , and also for geometric computer vision problems such as optical(More)
Higher frame-rates promise better tracking of rapid motion, but advanced real-time vision systems rarely exceed the standard 10– 60Hz range, arguing that the computation required would be too great. Actually, increasing frame-rate is mitigated by reduced computational cost per frame in trackers which take advantage of prediction. Additionally , when we(More)
We describe a new method for comparing frame appearance in a frame-to-model 3-D mapping and tracking system using an low dynamic range (LDR) RGB-D camera which is robust to brightness changes caused by auto exposure. It is based on a normalised radiance measure which is invariant to exposure changes and not only robustifies the tracking under changing(More)
This paper deals with the tracking and following of a person with a camera mounted mobile robot. A modified energy based optical flow approach is used for motion segmentation from a pair of images. Further a spatial relative ve-olcity based filering is used to extract prominently moving objects. Depth and color information are also used to robustly identify(More)