Arthur Daniel Costea

Word Channel Based Multiscale Pedestrian Detection without Image Resizing and Using Only One Classifier

Most pedestrian detection approaches that achieve high accuracy and precision rate and that can be used for realtime applications are based on histograms of gradient orientations. Usually multiscale detection is attained by resizing the image several times and by recomputing the image features or using multiple classifiers for different scales. In this paper we present a pedestrian detection approach that uses the same classifier for all pedestrian scales based on image features computed for a single scale. We go beyond the low level pixel-wise gradient orientation bins and use higher level visual words organized into Word Channels. Boosting is used to learn classification features from the integral Word Channels. The proposed approach is evaluated on multiple datasets and achieves outstanding results on the INRIA and Caltech-USA benchmarks. By using a GPU implementation we achieve a classification rate of over 10 million bounding boxes per second and a 16 FPS rate for multiscale detection in a 640×480 image.

Semantic Channels for Fast Pedestrian Detection

Pedestrian detection and semantic segmentation are high potential tasks for many real-time applications. However most of the top performing approaches provide state of art results at high computational costs. In this work we propose a fast solution for achieving state of art results for both pedestrian detection and semantic segmentation. As baseline for pedestrian detection we use sliding windows over cost efficient multiresolution filtered LUV+HOG channels. We use the same channels for classifying pixels into eight semantic classes. Using short range and long range multiresolution channel features we achieve more robust segmentation results compared to traditional codebook based approaches at much lower computational costs. The resulting segmentations are used as additional semantic channels in order to achieve a more powerful pedestrian detector. To also achieve fast pedestrian detection we employ a multiscale detection scheme based on a single flexible pedestrian model and a single image scale. The proposed solution provides competitive results on both pedestrian detection and semantic segmentation benchmarks at 8 FPS on CPU and at 15 FPS on GPU, being the fastest top performing approach.

Fast Pedestrian Detection for Mobile Devices

In this paper we present a fast and robust solution for pedestrian detection that can run in real time conditions even on mobile devices with limited computational power. An optimization of the channel features based multiscale detection schemes is proposed by using 8 detection models for each half octave scales. The image features have to be computed only once each half octave and there is no need for feature approximation. We use multiscale square features for training the multiresolution pedestrian classifiers. The proposed solution achieves state of art detection results on Caltech pedestrian benchmark at over 100 FPS using a CPU implementation, being the fastest detection approach on the benchmark. The solution is fast enough to perform under real time conditions on mobile platforms, yet preserving its robustness. The full detection process can run at over 20 FPS on a quad-core ARM CPU based smartphone or tablet, being a suitable solution for limited computational power mobile devices or embedded platforms.

Multi-class segmentation for traffic scenarios at over 50 FPS

Multi-class segmentation assigns a class label to each pixel in an image. It represents a significant task for the semantic understanding of images and has received plentiful attention over the last years. The current state of art is dominated by conditional random field based approaches, defined over pixels or image segments. However, high accuracy segmentation comes at a high computational cost. The best performing methods can barely run at few frames per second and are far from real-time applications. Our goal is to bridge the gap between current state of the art segmentation approaches and real-time applications. In this paper we propose an efficient approach for individual pixel classification. Multiple local descriptors are computed densely and then quantized using visual codebooks. Joint boosting is used to classify each pixel based on the quantized local descriptors. We show that using careful design choices and GPU optimization we can achieve sate of the art segmentation results at over 50 FPS. We also propose a Conditional Random Field (CRF) model defined over superpixels that uses the proposed pixel classifier for the estimation of unary potentials. The CRF based multi-class segmentation can run at over 30 FPS. The proposed approach is validated on the MSRC21 and CamVid multi-class segmentation benchmarks, the former one consisting of urban traffic sequences.

Obstacle detection using stereovision for Android-based mobile devices

The increasing development of smart mobile devices has brought a new solution to improving driving assistance systems. In this paper, we present an approach for a real-time obstacle detection using stereovision on mobile devices. We started from the premises that regions in the image belonging to the same object have similar appearance and are close in the 3D space. The limitations introduced by the low-computational hardware of the mobile devices imposed the use of a sparse stereo reconstruction, followed by an efficient implementation of superpixel segmentation. The simple linear iterative clustering (SLIC) is well-suited for such applications extracting superpixels with fine precision. We detect the road and markings in order to remove them from the region of interest where potential obstacles are searched. In a further step, the 3D information obtained from stereo reconstruction allows the superpixels to be grouped in regions which belong to the same object. In conclusion, we managed to obtain accurate obstacle detection at short-medium distances and in low-speed traffic scenarios and most importantly real-time processing.

Fast traffic scene segmentation using multi-range features from multi-resolution filtered and spatial context channels

In this paper we describe a fast solution for the semantic segmentation of traffic scenarios. We propose a multiresolution filtering scheme over LUV + HOG image channels using high pass and low pass filtered channels at multiple scales. To add spatial context, we extend the filtered channels with horizontal and vertical position channels. We introduce multi-range classification features that capture local structure and context for achieving fast semantic segmentation of traffic scenarios. Binary boosting based pixel classifiers are trained for each semantic class. Finally, we use these classifiers to provide the unary potential term in a dense Conditional Random Field. We evaluate the proposed solution on the CamVid traffic scene segmentation benchmark and achieve state of art results at 25 FPS, being the fastest top performing approach.

Modeling and tracking of dynamic obstacles for logistic plants using omnidirectional stereo vision

In this work we present an obstacle detection and tracking solution applied to Automated Guided Vehicles (AGVs) in industrial environments. The proposed method relies on information provided by an omnidirectional stereo vision system enabling 360 degree perception around the AGV. The stereo data is transformed into a classified digital elevation map (DEM). Based on this intermediate representation we are able to generate a set of obstacle hypotheses, each represented by a 3D cuboid and a free-form polygonal model. The cuboidal model is used for the classification of each hypothesis as “Pedestrian”, “AGV”, “Large Obstacle” or “Small Obstacle”, while the free-form polylines are used for object motion estimation relying on an Iterative Closest Point (ICP) method. The obtained measurements are subjected to a Kalman filter based tracking approach, in which the data association takes into account also the classification results.

Obstacle localization and recognition for autonomous forklifts using omnidirectional stereovision

In this paper we propose an approach for obstacle localization and recognition using omnidirectional stereovision applied to autonomous fork-lifts in industrial environments. We use omnidirectional stereovision with two fisheye cameras for the 3D perception of the surrounding environment. Using the reconstructed 3D points, a Digital Elevation Map (DEM) is constructed consisting of a 2.5D grid of elevation cells. Each cell is then classified as ground or obstacle. Further, we use the classified DEM to generate obstacle hypotheses. To ensure a higher detection rate we also propose a fast sliding window based approach relying on the monocular fisheye intensity image. The detections from both approaches are merged and are subjected to a tracking mechanism. Finally each obstacle is classified using boosting over Visual Codebook type features. The classification is refined using the classification history available from tracking. The presented approaches are integrated into a 3D visual perception system for AGVs and are of real time performance.

Semi-automatic image annotation of street scenes

Scene labeling enables very sophisticated and powerful applications for autonomous driving. Training classifiers for this task would not be possible without the existence of large datasets of pixelwise labeled images. Manually annotating a large number of images is an expensive and time consuming process. In this paper, we propose a new semi-automatic annotation tool for scene labeling tailored for autonomous driving. This tool significantly reduces the effort of the annotator and also the time spent to annotate the data, while at the same time it offers the necessary features to produce precise pixel-level semantic labeling. The main contribution of our work represents the development of a complex annotation framework able to generate automatic annotations for 20 classes, which the user can control and modify accordingly. Automatic annotations are obtained in two separate ways. First, we employ a pixelwise fully-connected Conditional Random Field (CRF). Second, we perform grouping of similar neighboring superpixels based on 2D appearance and 3D information using a boosted classifier. Polygons represent the manual correction mechanism for the automatic annotations.

Improved autonomous load handling with stereo cameras

We present newly added modules for our autonomous load handling system. The stereo camera system provides information about the scene in front of the automated forklift. A new alternative module for pallet detection is described. Several processing modules for unloading operations are also presented. Our system is evaluated by means of detection rate and by performing field tests. The tests show that it is capable of providing a sufficiently accurate position of the pallets in order to perform loading and unloading operations in multiple scenarios.