Alhayat Ali Mekonnen

Fast HOG based person detection devoted to a mobile robot with a spherical camera

In this paper, we present a fast Histogram of Oriented Gradients (HOG) based person detector. The detector adopts a cascade of rejectors framework by selecting discriminant features via a new proposed feature selection framework based on Binary Integer Programming. The mathematical programming explicitly formulates an optimization problem to select discriminant features taking detection performance and computation time into account. The learning of the cascade classifier and its detection capability are validated using a proprietary dataset acquired using the Ladybug2 spherical camera and the public INRIA person detection dataset. The final detector achieves a comparable detection performance as Dalal and Triggs [2] detector while achieving on average more than 2.5×-8× speed up depending on the training dataset.

People Detection with Heterogeneous Features and Explicit Optimization on Computation Time

In this paper we present a novel people detector that employs discrete optimization for feature selection. Specifically, we use binary integer programming to mine heterogeneous features taking both detection performance and computation time explicitly into consideration. The final trained detector exhibits low Miss Rates with significant boost in frame rate. For example, it achieves a 2.6% less Miss Rate at 10-4 FPPW compared to Dalal and Triggs HOG detector with a 9.22x speed improvement.

Tracking-by-detection of multiple persons by a resample-move particle filter

Camera networks make an important component of modern complex perceptual systems with widespread applications spanning surveillance, human/machine interaction and healthcare. Smart cameras that can perform part of the perceptual data processing improve scalability in both processing power and network resources. Based on these insights, this paper presents a particle filter for multiple person tracking designed for an FPGA-based smart camera. We propose a new joint Markov Chain Monte Carlo-based particle filter (MCMC-PF) with short Markov chains, devoted to each individual particle, in order to sample the particle swarm in relevant regions of the high dimensional state-space with increased particle diversity. Finding an efficient sampling method has become another challenge when designing particle filters, especially for those devoted to more than two or three targets. A proposal distribution, combining diffusion dynamics, learned HOG + SVM person detections, and adaptive background mixture models, limits here the well-known burst in terms of particles and MCMC iterations. This informed proposal based on saliency maps has only been marginally used in the literature in a joint state space PF framework. The presented qualitative and quantitative results—for proprietary and public video datasets—clearly show that our tracker outperforms the well-known MCMC-PF in terms of (1) tracking performances, i.e. robustness and precision, and (2) parallelization capabilities as the MCMC-PF processes the particles sequentially.

Upper Body Detection and Feature Set Evaluation for Body Pose Classification

This work investigates some visual functionalities required in Human-Robot Interaction (HRI) to evaluate the intention of a person to interact with another agent (robot or human). Analyzing the upper part of the human body which includes the head and the shoulders, we obtain essential cues on the persons intention. We propose a fast and efficient upper body detector and an approach to estimate the upper body pose in 2D images. The upper body detector derived from a state-of-the-art pedestrian detector identifies people using Aggregated Channel Features (ACF) and fast feature pyramid whereas the upper body pose classifier uses a sparse representation technique to recognize their shoulder orientation. The proposed detector exhibits state-of-the-art result on a public dataset in terms of both detection performance and frame rate. We also present an evaluation of different feature set combinations for pose classification using upper body images and report promising results despite the associated challenges.

Perceiving user's intention-for-interaction: A probabilistic multimodal data fusion scheme

Understanding peoples intention, be it action or thought, plays a fundamental role in establishing coherent communication amongst people, especially in non-proactive robotics, where the robot has to understand explicitly when to start an interaction in a natural way. In this work, a novel approach is presented to detect peoples intention-for-interaction. The proposed detector fuses multimodal cues, including estimated head pose, shoulder orientation and vocal activity detection, using a probabilistic discrete state Hidden Markov Model. The multimodal detector achieves up to 80% correct detection rates improving purely audio and RGB-D based variants.

Trade-off Between GPGPU based Implementations of Multi Object Tracking Particle Filter.

In this work, we present the design, analysis and implementation of a decentralized particle filter (DPF) for multiple object tracking (MOT) on a graphics processing unit (GPU). We investigate two variants of the implementation , their advantages and caveats in terms of scaling with larger particle numbers and performance on several datasets. First we compare the precision of our GPU implementation with standard CPU version. Next we compare performance of the GPU variants under different scenarios. The results show the GPU variant leads to a five fold speedup on average (in best cases the speedup reaches a factor of 18) over the CPU variant while keeping similar tracking accuracy and precision.

Mean Response-Time Minimization of a Soft-Cascade Detector

In this paper, the problem of minimizing the mean response-time of a soft-cascade detector is addressed. A soft-cascade detector is a machine learning tool used in applications that need to recognize the presence of certain types of object instances in images. Classical soft-cascade learning methods select the weak classifiers that compose the cascade, as well as the classification thresholds applied at each cascade level, so that a desired detection performance is reached. They usually do not take into account its mean response-time, which is also of importance in time-constrained applications. To overcome that, we consider the threshold selection problem aiming to minimize the computation time needed to detect a target object in an image (i.e., by classifying a set of samples). We prove the NP-hardness of the problem and propose a mathematical model that takes benefit from several dominance properties, which are put into evidence. On the basis of computational experiments, we show that we can provide a faster cascade detector, while maintaining the same detection performances.

Incorporating Computation Time Measures during Heterogeneous Features Selection in a Boosted Cascade People Detector

In this paper, we investigate the notion of incorporating feature computation time measures during feature selection in a boosted cascade people detector utilizing heterogeneous pool of features. We present various approaches based on pareto-front analysis, computation time weighted Adaboost, and Binary Integer Programming (BIP) with comparative evaluations. The novel feature selection method proposed based on BIP – the main contribution – mines heterogeneous features taking both detection performance and computation time explicitly into consideration. The results demonstrate that the detector using this feature selection scheme exhibits low miss rates with significant boost in frame rate. For example, it achieves a 2.6% less miss rate at 10e−4 FPPW compared to Dalal and Triggs HOG detector with a 9.22x speed improvement. The presented extensive experimental results clearly highlight the improvements the proposed framework brings to the table.

Pareto-Front Analysis and AdaBoost for Person Detection Using Heterogeneous Features

In this paper, a boosted cascade person detection framework with heterogeneous pool of features is presented. The framework unveils a new feature selection scheme based on Pareto-Front analysis and AdaBoost. At each cascade node, Pareto-Front analysis is used to select dominant features thereby reducing the total number of features to a size easily manageable by AdaBoost. The final detector achieves a very low Miss Rate of 0.07 at 10-4 False Positives Per Window on the INRIA public dataset.