Sebastian Houben

Detection of traffic signs in real-world images: The German traffic sign detection benchmark

Real-time detection of traffic signs, the task of pinpointing a traffic signs location in natural images, is a challenging computer vision task of high industrial relevance. Various algorithms have been proposed, and advanced driver assistance systems supporting detection and recognition of traffic signs have reached the market. Despite the many competing approaches, there is no clear consensus on what the state-of-the-art in this field is. This can be accounted to the lack of comprehensive, unbiased comparisons of those methods. We aim at closing this gap by the “German Traffic Sign Detection Benchmark” presented as a competition at IJCNN 2013 (International Joint Conference on Neural Networks). We introduce a real-world benchmark data set for traffic sign detection together with carefully chosen evaluation metrics, baseline results, and a web-interface for comparing approaches. In our evaluation, we separate sign detection from classification, but still measure the performance on relevant categories of signs to allow for benchmarking specialized solutions. The considered baseline algorithms represent some of the most popular detection approaches such as the Viola-Jones detector based on Haar features and a linear classifier relying on HOG descriptors. Further, a recently proposed problem-specific algorithm exploiting shape and color in a model-based Houghlike voting scheme is evaluated. Finally, we present the best-performing algorithms of the IJCNN competition.

A single target voting scheme for traffic sign detection

Traffic sign detection and recognition is an important part of advanced driver assistance systems. Many prototype solutions for this task have been developed, and first commercial systems have just become available. Their image processing chain can be devided into three steps, preprocessing, detection, and recognition. Albeit several reliable sign recognition algorithms exist by now sign detection under real-world conditions is still unstable. Therefore, we address the first two steps of the processing chain presenting an analysis of widely used detectors, namely Hough-like methods. We evaluate several preprocessing steps and tweaks to increase their performance. Hence, the detectors are applied to a large, publicly available set of images from real-life traffic scenes. As main result we establish a new probabilistic measure for traffic sign colour detection and, based on the findings in our analysis, propose a novel Hough-like algorithm for detecting circular and triangular shapes. These improvements significantly increased detection performance in our experiments.

On-vehicle video-based parking lot recognition with fisheye optics

The search for free parking space in a crowded car park is a time-consuming and tedious task. Todays park assistance systems provide the driver with acoustic or visual feedback when approaching an obstacle or semi-autonomously navigate the vehicle into the parking lot. However, finding a free parking lot is usually left to the driver. In this paper, we address this search problem via video sensors only. This can be used as a help to the driver to quickly pass a parking deck and, more important, can be regarded as a cornerstone to fully autonomously parking vehicles.

Towards highly automated driving in a parking garage: General object localization and tracking using an environment-embedded camera system

In this study, we present a new indoor positioning and environment perception system for generic objects based on multiple surveillance cameras. In order to assist highly automated driving, our system detects the vehicles position and any object along its current path to avoid collisions. A main advantage of the proposed approach is the usage of cameras that are already installed in the majority of parking garages. We generate precise object hypotheses in 3D world coordinates based on a given extrinsic camera calibration. Starting with a background subtraction algorithm for the segmentation of each camera image, we propose a robust view-ray intersection approach that enables the system to match and triangulate segmented hypotheses from all cameras. Comparing with LIDAR-based ground truth, we were able to evaluate the systems mean localization accuracy of 0.37 m for a variety of different sequences.

Video-based trailer detection and articulation estimation

Even for experienced drivers handling a roll trailer with a passenger car is a difficult and often tedious task. Moreover, the driver needs to keep track of the trailers driving stability on unsteady roads. There are driver assistance systems that can simplify trajectory planning and observe the oscillation amplitude, but they require additional hardware. In this paper, we present a method for trailer detection and articulation angle measurement based on video data from a rear end wide-angle camera. It consists of two stages: to decide whether or not a trailer is coupled to the vehicle and to estimate its articulation angle. These calculations work on single video frames. The vehicle is therefore not required to be in motion. However, we stabilize the single frame estimations by temporal integration. We perform training and parameter optimization and evaluate the accuracy of our approach by comparing the results to those of an articulation measurement unit attached to a test vehicles hitch. Results show that it can very reliably be determined whether or not a trailer is coupled to the vehicle. Furthermore, its articulation can be estimated with a mean error of less than two degrees.

Arbitrary object localization and tracking via multiple-camera surveillance system embedded in a parking garage

We illustrate a multiple-camera surveillance system installed in a parking garage to detect arbitrary moving objects. Our system is real-time capable and computes precise and reliable object positions. These objects are tracked to warn of collisions, e.g. between vehicles, pedestrians or other vehicles. The proposed system is based on multiple grayscale cameras connected by a local area network. Each camera shares its field of view with other cameras to handle occlusions and to enable multi-view vision. We aim at using already installed hardware found in many modern public parking garages. The system’s pipeline starts with the synchronized image capturing process separately for each camera. In the next step, moving objects are selected by a foreground segmentation approach. Subsequently, the foreground objects from a single camera are transformed into view rays in a common world coordinate system and are joined to receive plausible object hypotheses. This transformation requires a one-time initial intrinsic and extrinsic calibration beforehand. Afterwards, these view rays are filtered temporally to arrive at continuous object tracks. In our experiments we used a precise LIDAR-based reference system to evaluate and quantify the proposed system’s precision with a mean localization accuracy of 0.24m for different scenarios.

Park marking-based vehicle self-localization with a fisheye topview system

Accurately self-localizing a vehicle is of high importance as it allows to robustify nearly all modern driver assistance functionality, e.g., lane keeping and coordinated autonomous driving maneuvers. We examine vehicle self-localization relying only on video sensors, in particular, a system of four fisheye cameras providing a view surrounding the car, a setup currently growing popular in upper-class cars. The presented work aims at an autonomous parking scenario. The method is based on park markings as orientation marks since they can be found in nearly every parking deck and require only little additional preparation. Our contribution is twofold: (1) we present a new real-time capable image processing pipeline for topview systems extracting park markings and show how to obtain a reliable and accurate ego pose and ego motion estimation given a coarse pose as starting point. (2) The aptitude of this often neglected sensor array for vehicle self-localization is demonstrated. Experimental evaluation yields a precision of 0.15

Topview stereo: combining vehicle-mounted wide-angle cameras to a distance sensor array

\pm