Heiko Hirschmüller

Stereo Processing by Semiglobal Matching and Mutual Information

This paper describes the Semi-Global Matching (SGM) stereo method. It uses a pixelwise, Mutual Information based matching cost for compensating radiometric differences of input images. Pixelwise matching is supported by a smoothness constraint that is usually expressed as a global cost function. SGM performs a fast approximation by pathwise optimizations from all directions. The discussion also addresses occlusion detection, subpixel refinement and multi-baseline matching. Additionally, postprocessing steps for removing outliers, recovering from specific problems of structured environments and the interpolation of gaps are presented. Finally, strategies for processing almost arbitrarily large images and fusion of disparity images using orthographic projection are proposed.A comparison on standard stereo images shows that SGM is among the currently top-ranked algorithms and is best, if subpixel accuracy is considered. The complexity is linear to the number of pixels and disparity range, which results in a runtime of just 1-2s on typical test images. An in depth evaluation of the Mutual Information based matching cost demonstrates a tolerance against a wide range of radiometric transformations. Finally, examples of reconstructions from huge aerial frame and pushbroom images demonstrate that the presented ideas are working well on practical problems.

Accurate and efficient stereo processing by semi-global matching and mutual information

This paper considers the objectives of accurate stereo matching, especially at object boundaries, robustness against recording or illumination changes and efficiency of the calculation. These objectives lead to the proposed semi-global matching method that performs pixelwise matching based on mutual information and the approximation of a global smoothness constraint. Occlusions are detected and disparities determined with sub-pixel accuracy. Additionally, an extension for multi-baseline stereo images is presented. There are two novel contributions. Firstly, a hierarchical calculation of mutual information based matching is shown, which is almost as fast as intensity based matching. Secondly, an approximation of a global cost calculation is proposed that can be performed in a time that is linear to the number of pixels and disparities. The implementation requires just 1 second on typical images.

Evaluation of Cost Functions for Stereo Matching

Stereo correspondence methods rely on matching costs for computing the similarity of image locations. In this paper we evaluate the insensitivity of different matching costs with respect to radiometric variations of the input images. We consider both pixel-based and window-based variants and measure their performance in the presence of global intensity changes (e.g., due to gain and exposure differences), local intensity changes (e.g., due to vignetting, non-Lambertian surfaces, and varying lighting), and noise. Using existing stereo datasets with ground-truth disparities as well as six new datasets taken under controlled changes of exposure and lighting, we evaluate the different costs with a local, a semi-global, and a global stereo method.

Evaluation of Stereo Matching Costs on Images with Radiometric Differences

Stereo correspondence methods rely on matching costs for computing the similarity of image locations. We evaluate the insensitivity of different costs for passive binocular stereo methods with respect to radiometric variations of the input images. We consider both pixel-based and window-based variants like the absolute difference, the sampling-insensitive absolute difference, and normalized cross correlation, as well as their zero-mean versions. We also consider filters like LoG, mean, and bilateral background subtraction (BilSub) and nonparametric measures like Rank, SoftRank, Census, and Ordinal. Finally, hierarchical mutual information (HMI) is considered as pixelwise cost. Using stereo data sets with ground-truth disparities taken under controlled changes of exposure and lighting, we evaluate the costs with a local, a semiglobal, and a global stereo method. We measure the performance of all costs in the presence of simulated and real radiometric differences, including exposure differences, vignetting, varying lighting, and noise. Overall, the ranking of methods across all data sets and experiments appears to be consistent. Among the best costs are BilSub, which performs consistently very well for low radiometric differences; HMI, which is slightly better as pixelwise matching cost in some cases and for strong image noise; and Census, which showed the best and most robust overall performance.

High-Resolution Stereo Datasets with Subpixel-Accurate Ground Truth

We present a structured lighting system for creating high-resolution stereo datasets of static indoor scenes with highly accurate ground-truth disparities. The system includes novel techniques for efficient 2D subpixel correspondence search and self-calibration of cameras and projectors with modeling of lens distortion. Combining disparity estimates from multiple projector positions we are able to achieve a disparity accuracy of 0.2 pixels on most observed surfaces, including in half-occluded regions. We contribute 33 new 6-megapixel datasets obtained with our system and demonstrate that they present new challenges for the next generation of stereo algorithms.

A Humanoid Two-Arm System for Dexterous Manipulation

This paper presents a humanoid two-arm system developed as a research platform for studying dexterous two-handed manipulation. The system is based on the modular DLR-Lightweight-Robot-III and the DLR-Hand-II. Two arms and hands are combined with a three degrees-of-freedom movable torso and a visual system to form a complete humanoid upper body. In this paper we present the design considerations and give an overview of the different sub-systems. Then, we describe the requirements on the software architecture. Moreover, the applied control methods for two-armed manipulation and the vision algorithms used for scene analysis are discussed

Stereo Vision in Structured Environments by Consistent Semi-Global Matching

This paper considers the use of stereo vision in structured environments. Sharp discontinuities and large untextured areas must be anticipated, but complex or natural shapes of objects and fine structures should be handled as well. Additionally, radiometric differences of input images often occur in practice. Finally, computation time is an issue for handling large or many images in acceptable time. The Semi-Global Matching method is chosen as it fulfills already many of the requirements. Remaining problems in structured environments are carefully analyzed and two novel extensions suggested. Firstly, intensity consistent disparity selection is proposed for handling untextured areas. Secondly, discontinuity preserving interpolation is suggested for filling holes in the disparity images that are caused by some filters. It is shown that the performance of the new method on test images with ground truth is comparable to the currently best stereo methods, but the complexity and runtime is much lower.

Mutual Information Based Semi-Global Stereo Matching on the GPU

Real-time stereo matching is necessary for many practical applications, including robotics. There are already many real-time stereo systems, but they typically use local approaches that cause object boundaries to be blurred and small objects to be removed. We have selected the Semi-Global Matching (SGM) method for implementation on graphics hardware, because it can compete with the currently best global stereo methods. At the same time, it is much more efficient than most other methods that produce a similar quality. In contrast to previous work, we have fully implemented SGM including matching with mutual information, which is partly responsible for the high quality of disparity images. Our implementation reaches 4.2 fps on a GeForce 8800 ULTRA with images of 640 ×480 pixel size and 128 pixel disparity range and 13 fps on images of 320 ×240 pixel size and 64 pixel disparity range.

Stereo vision based indoor/outdoor navigation for flying robots

We introduce our new quadrotor platform for realizing autonomous navigation in unknown indoor/outdoor environments. Autonomous waypoint navigation, obstacle avoidance and flight control is implemented on-board. The system does not require a special environment, artificial markers or an external reference system. We developed a monolithic, mechanically damped perception unit which is equipped with a stereo camera pair, an Inertial Measurement Unit (IMU), two processor-and an FPGA board. Stereo images are processed on the FPGA by the Semi-Global Matching algorithm. Keyframe-based stereo odometry is fused with IMU data compensating for time delays that are induced by the vision pipeline. The system state estimate is used for control and on-board 3D mapping. An operator can set waypoints in the map, while the quadrotor autonomously plans its path avoiding obstacles. We show experiments with the quadrotor flying from inside a building to the outside and vice versa, traversing a window and a door respectively. A video of the experiments is part of this work. To the best of our knowledge, this is the first autonomously flying system with complete on-board processing that performs waypoint navigation with obstacle avoidance in geometrically unconstrained, complex indoor/outdoor environments.

Autonomous Vision-based Micro Air Vehicle for Indoor and Outdoor Navigation

Micro air vehicles have become very popular in recent years. Autonomous navigation of such systems plays an important role in many industrial applications as well as in search-and-rescue scenarios. We present a quadrotor that performs autonomous navigation in complex indoor and outdoor environments. An operator selects target positions in the onboard map and the system autonomously plans an obstacle-free path and flies to these locations. An onboard stereo camera and inertial measurement unit are the only sensors. The system is independent of external navigation aids such as GPS. No assumptions are made about the structure of the unknown environment. All navigation tasks are implemented onboard the system. A wireless connection is only used for sending images and a three-dimensional 3D map to the operator and to receive target locations. We discuss the hardware and software setup of the system in detail. Highlights of the implementation are the field-programmable-gate-array-based dense stereo matching of 0.5 Mpixel images at a rate of 14.6 Hz using semiglobal matching, locally drift-free visual odometry with key frames, and sensor data fusion with compensation of measurement delays of 220i¾?ms. We show the robustness of the approach in simulations and experiments with ground truth. We present the results of a complex, autonomous indoor/outdoor flight and the exploration of a coal mine with obstacle avoidance and 3D mapping.