Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via convolutional networks to disparity and scene flow estimation. To this end, we propose three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks. Our datasets are the first large-scale datasets to enable training and evaluating scene flow methods. Besides the datasets, we present a convolutional network for real-time disparity estimation that provides state-of-the-art results. By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.

A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation

We propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images. We leverage knowledge of the problem’s geometry to form a cost volume using deep feature representations. We learn to incorporate contextual information using 3-D convolutions over this volume. Disparity values are regressed from the cost volume using a proposed differentiable soft argmin operation, which allows us to train our method end-to-end to sub-pixel accuracy without any additional post-processing or regularization. We evaluate our method on the Scene Flow and KITTI datasets and on KITTI we set a new stateof-the-art benchmark, while being significantly faster than competing approaches.

End-to-End Learning of Geometry and Context for Deep Stereo Regression

Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated dataset. The present paper extends the concept of optical flow estimation via convolutional networks to disparity and scene flow estimation. To this end, we propose three synthetic stereo video datasets with sufficient realism, variation, and size to successfully train large networks. Our datasets are the first large-scale datasets to enable training and evaluation of scene flow methods. Besides the datasets, we present a convolutional network for real-time disparity estimation that provides state-of-the-art results. By combining a flow and disparity estimation network and training it jointly, we demonstrate the first scene flow estimation with a convolutional network.

/pdf/a-large-dataset-to-train-convolutional-networks-for-3gh130387u.pdf

In the past year, convolutional neural networks have been shown to perform extremely well for stereo estimation. However, current architectures rely on siamese networks which exploit concatenation followed by further processing layers, requiring a minute of GPU computation per image pair. In contrast, in this paper we propose a matching network which is able to produce very accurate results in less than a second of GPU computation. Towards this goal, we exploit a product layer which simply computes the inner product between the two representations of a siamese architecture. We train our network by treating the problem as multi-class classification, where the classes are all possible disparities. This allows us to get calibrated scores, which result in much better matching performance when compared to existing approaches.

/pdf/efficient-deep-learning-for-stereo-matching-2r0deb59uz.pdf

Efficient Deep Learning for Stereo Matching

This paper provides a review of the literature in on-road vision-based vehicle detection, tracking, and behavior understanding. Over the past decade, vision-based surround perception has progressed from its infancy into maturity. We provide a survey of recent works in the literature, placing vision-based vehicle detection in the context of sensor-based on-road surround analysis. We detail advances in vehicle detection, discussing monocular, stereo vision, and active sensor-vision fusion for on-road vehicle detection. We discuss vision-based vehicle tracking in the monocular and stereo-vision domains, analyzing filtering, estimation, and dynamical models. We discuss the nascent branch of intelligent vehicles research concerned with utilizing spatiotemporal measurements, trajectories, and various features to characterize on-road behavior. We provide a discussion on the state of the art, detail common performance metrics and benchmarks, and provide perspective on future research directions in the field.

https://cvrr.ucsd.edu/publications/2013/SayananTrivedi_IEEETITS2013_VehicleSurvey.pdf

Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis

The computation of stereoscopic depth is an important field of computer vision. Although a large variety of algorithms has been developed, the traditional correlation-based versions of these algorithms are prevalent. This is mainly due to easy implementation and handling but also to the linear computational complexity, as compared to more elaborated algorithms based on diffusion processes, graph-cut or bilateral filtering. In this paper, we introduce a new two-stage matching cost for the traditional approach: the summed normalized cross-correlation (SNCC). This new cost function performs a normalized cross-correlation in the first stage and aggregates the correlation values in a second stage. We show that this new measure can be implemented efficiently and that it leads to a substantial improvement of the performance of the traditional stereo approach because it is less sensitive to high contrast outliers.

A Two-Stage Correlation Method for Stereoscopic Depth Estimation

Spacecraft collision avoidance procedures have become an essential part of satellite operations. Complex and constantly updated estimates of the collision risk between orbiting objects inform various operators who can then plan risk mitigation measures. Such measures can be aided by the development of suitable machine learning (ML) models that predict, for example, the evolution of the collision risk over time. In October 2019, in an attempt to study this opportunity, the European Space Agency released a large curated dataset containing information about close approach events in the form of conjunction data messages (CDMs), which was collected from 2015 to 2019. This dataset was used in the Spacecraft Collision Avoidance Challenge, which was an ML competition where participants had to build models to predict the final collision risk between orbiting objects. This paper describes the design and results of the competition and discusses the challenges and lessons learned when applying ML methods to this problem domain.

/pdf/spacecraft-collision-avoidance-challenge-design-and-results-4xit5jb3yg.pdf

Spacecraft collision avoidance challenge: Design and results of a machine learning competition

The present invention proposes a profound user-mower interaction, which enables the user to teach a robotic lawn mower for improving its visual obstacle detection. The main idea of the invention is that the user can show some typical obstacles from his garden to the mower. This will increases the performance of the visual obstacle detection. In the simplest scenario the user just places the mower in front of an obstacle, and activates the learning mechanism of the classification means (module) of the mower. The increasing use of smart devices such as smart phones or tablets enables also more elaborated learning. For example, the mower can send the input image to the smart device, and the user can provide a detailed annotation of the image. This will drastically improve the learning, because the mower is provided with ground truth information.

Trainable autonomous lawn mower

A method is proposed for detecting the position of a target object (51) in the environment of a host vehicle, comprising the following steps: - receiving a first position (6) of the target object as detected by an object position sensor (2) like e.g. a radar sensor, - receiving an image (7) containing the target object as detected by an image sensor (3) like e.g. a camera, - projecting the first position (6) on the image (7), and - refining the first position (6) by computing a second position (25) of the target object on the basis of a symmetry search within the image (7).

Vehicle with improved traffic-object position detection

The present invention presents a method and system for an autonomous mower attached with a camera, wherein the control of the parameters of the camera and the control of the mower movement and grass detection are optimized holistically during operation. The present invention mitigates the camera sensing limits by adapting the movement speed of the mower. Furthermore, the camera control optimizes the visibility of grass by using the grass mask of a grass segmentation to calculate updated exposure, gain and aperture values only from grass pixels. The grass segmentation tracks changes in the grass color that are caused by illumination differences. Optionally, the system is equipped with a head light used to further improve the camera signal quality in conjunction with the control of the camera parameters and the movement speed of the mower.

System, method and apparatus for unsupervised adaptation of the perception of an autonomous mower

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Nils Einecke

Author Tools

Chat about Author