Markus Mathias

Pedestrian detection at 100 frames per second

We present a new pedestrian detector that improves both in speed and quality over state-of-the-art. By efficiently handling different scales and transferring computation from test time to training time, detection speed is improved. When processing monocular images, our system provides high quality detections at 50 fps. We also propose a new method for exploiting geometric context extracted from stereo images. On a single CPU+GPU desktop machine, we reach 135 fps, when processing street scenes, from rectified input to detections output.

Face Detection without Bells and Whistles

Face detection is a mature problem in computer vision. While diverse high performing face detectors have been proposed in the past, we present two surprising new top performance results. First, we show that a properly trained vanilla DPM reaches top performance, improving over commercial and research systems. Second, we show that a detector based on rigid templates - similar in structure to the Viola&Jones detector - can reach similar top performance on this task. Importantly, we discuss issues with existing evaluation benchmark and propose an improved procedure.

Traffic sign recognition — How far are we from the solution?

Traffic sign recognition has been a recurring application domain for visual objects detection. The public datasets have only recently reached large enough size and variety to enable proper empirical studies. We revisit the topic by showing how modern methods perform on two large detection and classification datasets (thousand of images, tens of categories) captured in Belgium and Germany. We show that, without any application specific modification, existing methods for pedestrian detection, and for digit and face classification; can reach performances in the range of 95% ~ 99% of the perfect solution. We show detailed experiments and discuss the trade-off of different options. Our top performing methods use modern variants of HOG features for detection, and sparse representations for classification.

A three-layered approach to facade parsing

We propose a novel three-layered approach for semantic segmentation of building facades. In the first layer, starting from an oversegmentation of a facade, we employ the recently introduced machine learning technique Recursive Neural Networks (RNN) to obtain a probabilistic interpretation of each segment. In the second layer, initial labeling is augmented with the information coming from specialized facade component detectors. The information is merged using a Markov Random Field. In the third layer, we introduce weak architectural knowledge, which enforces the final reconstruction to be architecturally plausible and consistent. Rigorous tests performed on two existing datasets of building facades demonstrate that we significantly outperform the current-state of the art, even when using outputs from earlier layers of the pipeline. Also, we show how the final output of the third layer can be used to create a procedural reconstruction.

Handling Occlusions with Franken-Classifiers

Detecting partially occluded pedestrians is challenging. A common practice to maximize detection quality is to train a set of occlusion-specific classifiers, each for a certain amount and type of occlusion. Since training classifiers is expensive, only a handful are typically trained. We show that by using many occlusion-specific classifiers, we outperform previous approaches on three pedestrian datasets, INRIA, ETH, and Caltech USA. We present a new approach to train such classifiers. By reusing computations among different training stages, 16 occlusion-specific classifiers can be trained at only one tenth the cost of one full training. We show that also test time cost grows sub-linearly.

Fast stixel computation for fast pedestrian detection

Applications using pedestrian detection in street scene require both high speed and quality. Maximal speed is reached when exploiting the geometric information provided by stereo cameras. Yet, extracting useful information at speeds higher than 100 Hz is a non-trivial task. We propose a method to estimate the ground-obstacles boundary (and its distance), without computing a depth map. By properly parametrizing the search space in the image plane we improve the algorithmic performance, and reach speeds of

ATLAS: A Three-Layered Approach to Facade Parsing

200\ \mbox{Hz}

Seeking the Strongest Rigid Detector

on a desktop CPU. When connected with a state of the art GPU objects detector, we reach high quality detections at the record speed of

Procedural 3D Building Reconstruction Using Shape Grammars and Detectors

165\ \mbox{Hz}

AUTOMATIC ARCHITECTURAL STYLE RECOGNITION

.