Today, visual recognition systems are still rarely employed in robotics applications. Perhaps one of the main reasons for this is the lack of demanding benchmarks that mimic such scenarios. In this paper, we take advantage of our autonomous driving platform to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection. Our recording platform is equipped with four high resolution video cameras, a Velodyne laser scanner and a state-of-the-art localization system. Our benchmarks comprise 389 stereo and optical flow image pairs, stereo visual odometry sequences of 39.2 km length, and more than 200k 3D object annotations captured in cluttered scenarios (up to 15 cars and 30 pedestrians are visible per image). Results from state-of-the-art algorithms reveal that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world. Our goal is to reduce this bias by providing challenging benchmarks with novel difficulties to the computer vision community. Our benchmarks are available online at: www.cvlibs.net/datasets/kitti

/pdf/are-we-ready-for-autonomous-driving-the-kitti-vision-zygefho352.pdf

Are we ready for autonomous driving? The KITTI vision benchmark suite

This paper proposes a novel model and dataset for 3D scene flow estimation with an application to autonomous driving. Taking advantage of the fact that outdoor scenes often decompose into a small number of independently moving objects, we represent each element in the scene by its rigid motion parameters and each superpixel by a 3D plane as well as an index to the corresponding object. This minimal representation increases robustness and leads to a discrete-continuous CRF where the data term decomposes into pairwise potentials between superpixels and objects. Moreover, our model intrinsically segments the scene into its constituting dynamic components. We demonstrate the performance of our model on existing benchmarks as well as a novel realistic dataset with scene flow ground truth. We obtain this dataset by annotating 400 dynamic scenes from the KITTI raw data collection using detailed 3D CAD models for all vehicles in motion. Our experiments also reveal novel challenges which cannot be handled by existing methods.

/pdf/object-scene-flow-for-autonomous-vehicles-41p3or945d.pdf

Object scene flow for autonomous vehicles

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

R J Baxter 1982 London: Academic xii + 486 pp price £43.60 Over the past few years there has been a growing belief that all the twodimensional lattice statistical models will eventually be solved and that it will be Professor Baxter who solves them. Baxter has inherited the mantle of Onsager who started the process by solving exactly the two-dimensional Ising model in 1944.

Exactly Solved Models in Statistical Mechanics

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

We propose a novel two-step convolutional neural network to estimate a heart rate from a sequence of facial images. The network is trained end-to-end by alternating optimization and validated on three publicly available datasets yielding state-of-the-art results against three baseline methods. The network performs better by a 40% margin to the state-of-the-art method on a newly collected dataset. A challenging dataset of 204 fitness-themed videos is introduced. The dataset is designed to test the robustness of heart rate estimation methods to illumination changes and subject’s motion. 17 subjects perform 4 activities (talking, rowing, exercising on a stationary bike and an elliptical trainer) in 3 lighting setups. Each activity is captured by two RGB web-cameras, one is placed on a tripod, the other is attached to the fitness machine which vibrates significantly. Subject’s age ranges from 20 to 53 years, the mean heart rate is ≈ 110, the standard deviation ≈ 25.

Visual Heart Rate Estimation with Convolutional Neural Network.

A simple seed growing algorithm for estimating scene flow in a stereo setup is presented. Two calibrated and synchronized cameras observe a scene and output a sequence of image pairs. The algorithm simultaneously computes a disparity map between the image pairs and optical flow maps between consecutive images. This, together with calibration data, is an equivalent representation of the 3D scene flow, i.e. a 3D velocity vector is associated with each reconstructed point. The proposed method starts from correspondence seeds and propagates these correspondences to their neighborhood. It is accurate for complex scenes with large motions and produces temporally-coherent stereo disparity and optical flow results. The algorithm is fast due to inherent search space reduction. An explicit comparison with recent methods of spatiotemporal stereo and variational optical and scene flow is provided.

/pdf/scene-flow-estimation-by-growing-correspondence-seeds-5857fdhmtc.pdf

Scene flow estimation by growing correspondence seeds

A simple stereo matching algorithm is proposed that visits only a small fraction of disparity space in order to find a semi-dense disparity map. It works by growing from a small set of correspondence seeds. Unlike in known seed-growing algorithms, it guarantees matching accuracy and correctness, even in the presence of repetitive patterns. This success is based on the fact it solves a global optimization task. The algorithm can recover from wrong initial seeds to the extent they can even be random. The quality of correspondence seeds influences computing time, not the quality of the final disparity map. We show that the proposed algorithm achieves similar results as an exhaustive disparity space search but it is two orders of magnitude faster. This is very unlike the existing growing algorithms which are fast but erroneous. Accurate matching on 2-megapixel images of complex scenes is routinely obtained in a few seconds on a common PC from a small number of seeds, without limiting the disparity search range.

/pdf/efficient-sampling-of-disparity-space-for-fast-and-accurate-2nrx4z1swm.pdf

Efficient Sampling of Disparity Space for Fast And Accurate Matching

In many retrieval, object recognition, and wide-baseline stereo methods, correspondences of interest points (distinguished regions) are commonly established by matching compact descriptors such as SIFTs. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that 1) has high precision (is highly discriminative), 2) has good recall, and 3) is fast. The sequential decision on the correctness of a correspondence is based on simple statistics of a modified dense stereo matching algorithm. The statistics are projected on a prominent discriminative direction by SVM. Wald's sequential probability ratio test is performed on the SVM projection computed on progressively larger cosegmented regions. We show experimentally that the proposed sequential correspondence verification (SCV) algorithm significantly outperforms the standard correspondence selection method based on SIFT distance ratios on challenging matching problems.

/pdf/efficient-sequential-correspondence-selection-by-4fc52lvnsv.pdf

Efficient sequential correspondence selection by cosegmentation

3D Shape matching is an important problem in computer vision. One of the major difficulties in finding dense correspondences between 3D shapes is related to the topological discrepancies that often arise due to complex kinematic motions. In this paper we propose a shape matching method that is robust to such changes in topology. The algorithm starts from a sparse set of seed matches and outputs dense matching. We propose to use a shape descriptor based on properties of the heat-kernel and which provides an intrinsic scale-space representation. This descriptor incorporates (i) heat-flow from already matched points and (ii) self diffusion. At small scales the descriptor behaves locally and hence it is robust to global changes in topology. Therefore, it can be used to build a vertex-to-vertex matching score conditioned by an initial correspondence set. This score is then used to iteratively add new correspondences based on a novel seed-growing method that iteratively propagates the seed correspondences to nearby vertices. The matching is farther densified via an EM-like method that explores the congruency between the two shape embeddings. Our method is compared with two recently proposed algorithms and we show that we can deal with substantial topological differences between the two shapes.

/pdf/topologically-robust-3d-shape-matching-based-on-diffusion-1gnre1ngev.pdf

Jan Cech

Papers

Visual Heart Rate Estimation with Convolutional Neural Network.

Scene flow estimation by growing correspondence seeds

Efficient Sampling of Disparity Space for Fast And Accurate Matching

Efficient sequential correspondence selection by cosegmentation

Topologically-robust 3D shape matching based on diffusion geometry and seed growing