Markus Enzweiler

Monocular Pedestrian Detection: Survey and Experiments

Pedestrian detection is a rapidly evolving area in computer vision with key applications in intelligent vehicles, surveillance, and advanced robotics. The objective of this paper is to provide an overview of the current state of the art from both methodological and experimental perspectives. The first part of the paper consists of a survey. We cover the main components of a pedestrian detection system and the underlying models. The second (and larger) part of the paper contains a corresponding experimental study. We consider a diverse set of state-of-the-art systems: wavelet-based AdaBoost cascade, HOG/linSVM, NN/LRF, and combined shape-texture detection. Experiments are performed on an extensive data set captured onboard a vehicle driving through urban environment. The data set includes many thousands of training samples as well as a 27-minute test sequence involving more than 20,000 images with annotated pedestrian locations. We consider a generic evaluation setting and one specific to pedestrian detection onboard a vehicle. Results indicate a clear advantage of HOG/linSVM at higher image resolutions and lower processing speeds, and a superiority of the wavelet-based AdaBoost cascade approach at lower image resolutions and (near) real-time processing speeds. The data set (8.5 GB) is made public for benchmarking purposes.

The Cityscapes Dataset for Semantic Urban Scene Understanding

Visual understanding of complex urban street scenes is an enabling factor for a wide range of applications. Object detection has benefited enormously from large-scale datasets, especially in the context of deep learning. For semantic urban scene understanding, however, no current dataset adequately captures the complexity of real-world urban scenes. To address this, we introduce Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling. Cityscapes is comprised of a large, diverse set of stereo video sequences recorded in streets from 50 different cities. 5000 of these images have high quality pixel-level annotations, 20 000 additional images have coarse annotations to enable methods that leverage large volumes of weakly-labeled data. Crucially, our effort exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Our accompanying empirical study provides an in-depth analysis of the dataset characteristics, as well as a performance evaluation of several state-of-the-art approaches based on our benchmark.

Making Bertha Drive?An Autonomous Journey on a Historic Route

125 years after Bertha Benz completed the first overland journey in automotive history, the Mercedes Benz S-Class S 500 INTELLIGENT DRIVE followed the same route from Mannheim to Pforzheim, Germany, in fully autonomous manner. The autonomous vehicle was equipped with close-to-production sensor hardware and relied solely on vision and radar sensors in combination with accurate digital maps to obtain a comprehensive understanding of complex traffic situations. The historic Bertha Benz Memorial Route is particularly challenging for autonomous driving. The course taken by the autonomous vehicle had a length of 103 km and covered rural roads, 23 small villages and major cities (e.g. downtown Mannheim and Heidelberg). The route posed a large variety of difficult traffic scenarios including intersections with and without traffic lights, roundabouts, and narrow passages with oncoming traffic. This paper gives an overview of the autonomous vehicle and presents details on vision and radar-based perception, digital road maps and video-based self-localization, as well as motion planning in complex urban scenarios.

Multi-cue pedestrian classification with partial occlusion handling

This paper presents a novel mixture-of-experts framework for pedestrian classification with partial occlusion handling. The framework involves a set of component-based expert classifiers trained on features derived from intensity, depth and motion. To handle partial occlusion, we compute expert weights that are related to the degree of visibility of the associated component. This degree of visibility is determined by examining occlusion boundaries, i.e. discontinuities in depth and motion. Occlusion-dependent component weights allow to focus the combined decision of the mixture-of-experts classifier on the unoccluded body parts. In experiments on extensive real-world data sets, with both partially occluded and non-occluded pedestrians, we obtain significant performance boosts over state-of-the-art approaches by up to a factor of four in reduction of false positives at constant detection rates. The dataset is made public for benchmarking purposes.

A Multilevel Mixture-of-Experts Framework for Pedestrian Classification

Notwithstanding many years of progress, pedestrian recognition is still a difficult but important problem. We present a novel multilevel Mixture-of-Experts approach to combine information from multiple features and cues with the objective of improved pedestrian classification. On pose-level, shape cues based on Chamfer shape matching provide sample-dependent priors for a certain pedestrian view. On modality-level, we represent each data sample in terms of image intensity, (dense) depth, and (dense) flow. On feature-level, we consider histograms of oriented gradients (HOG) and local binary patterns (LBP). Multilayer perceptrons (MLP) and linear support vector machines (linSVM) are used as expert classifiers. Experiments are performed on a unique real-world multi-modality dataset captured from a moving vehicle in urban traffic. This dataset has been made public for research purposes. Our results show a significant performance boost of up to a factor of 42 in reduction of false positives at constant detection rates of our approach compared to a baseline intensity-only HOG/linSVM approach.

Making Bertha See

With the market introduction of the 2014 Mercedes-Benz S-Class vehicle equipped with a stereo camera system, autonomous driving has become a reality, at least in low speed highway scenarios. This raises hope for a fast evolution of autonomous driving that also extends to rural and urban traffic situations. In August 2013, an S-Class vehicle with close-to-production sensors drove completely autonomously for about 100 km from Mannheim to Pforzheim, Germany, following the well-known historic Bertha Benz Memorial Route. Next-generation stereo vision was the main sensing component and as such formed the basis for the indispensable comprehensive understanding of complex traffic situations, which are typical for narrow European villages. This successful experiment has proved both the maturity and the significance of machine vision for autonomous driving. This paper presents details of the employed vision algorithms for object recognition and tracking, free-space analysis, traffic light recognition, lane recognition, as well as self-localization.

The Benefits of Dense Stereo for Pedestrian Detection

This paper presents a novel pedestrian detection system for intelligent vehicles. We propose the use of dense stereo for both the generation of regions of interest and pedestrian classification. Dense stereo allows the dynamic estimation of camera parameters and the road profile, which, in turn, provides strong scene constraints on possible pedestrian locations. For classification, we extract spatial features (gradient orientation histograms) directly from dense depth and intensity images. Both modalities are represented in terms of individual feature spaces, in which discriminative classifiers (linear support vector machines) are learned. We refrain from the construction of a joint feature space but instead employ a fusion of depth and intensity on the classifier level. Our experiments involve challenging image data captured in complex urban environments (i.e., undulating roads and speed bumps). Our results show a performance improvement by up to a factor of 7.5 at the classification level and up to a factor of 5 at the tracking level (reduction in false alarms at constant detection rates) over a system with static scene constraints and intensity-only classification.

A mixed generative-discriminative framework for pedestrian classification

This paper presents a novel approach to pedestrian classification which involves utilizing the synthesized virtual samples of a learned generative model to enhance the classification performance of a discriminative model. Our generative model captures prior knowledge about the pedestrian class in terms of a number of probabilistic shape and texture models, each attuned to a particular pedestrian pose. Active learning provides the link between the generative and discriminative model, in the sense that the former is selectively sampled such that the training process is guided towards the most informative samples of the latter. In large-scale experiments on real-world datasets of tens of thousands of samples, we demonstrate a significant improvement in classification performance of the combined generative-discriminative approach over the discriminative-only approach (the latter exemplified by a neural network with local receptive fields and a support vector machine using Haar wavelet features).

Integrated pedestrian classification and orientation estimation

This paper presents a novel approach to single-frame pedestrian classification and orientation estimation. Unlike previous work which addressed classification and orientation separately with different models, our method involves a probabilistic framework to approach both in a unified fashion. We address both problems in terms of a set of view-related models which couple discriminative expert classifiers with sample-dependent priors, facilitating easy integration of other cues (e.g. motion, shape) in a Bayesian fashion. This mixture-of-experts formulation approximates the probability density of pedestrian orientation and scales-up to the use of multiple cameras. Experiments on large real-world data show a significant performance improvement in both pedestrian classification and orientation estimation of up to 50%, compared to state-of-the-art, using identical data and evaluation techniques.

Monocular pedestrian recognition using motion parallax

This paper presents a novel focus-of-attention strategy for monocular pedestrian recognition. It uses Bayespsila rule to estimate the posterior for the presence of a pedestrian in a certain (rectangular) image region, based on motion parallax features. This posterior is used as a parameter to control the amount of regions of interest (ROIs) that is passed to subsequent verification stages. For the latter, we use a state-of-the-art pedestrian recognition scheme which consists of multiple modules in a cascade architecture. We obtain optimized settings for the control parameters of the combined cascade system by a sequential ROC convex hull technique. Experiments are conducted on image data captured from a moving vehicle in an urban environment. We demonstrate that the proposed focus-of-attention strategy reduces the false positives of an otherwise identical monocular pedestrian recognition system by a factor of two, at equal detection rates. The overall system maintains processing rates close to real-time.