Djamel Merad

Fast People Counting Using Head Detection From Skeleton Graph

In this paper, we present a new method for counting people.This method is based on the head detection after asegmentation of the human body by skeleton graph process.The skeleton silhouette is computed and decomposed into aset of segments corresponding to the head , torso and limbs.This structure captures the minimal information about theskeleton shape. No assumption is made about the viewpoint,this is done after the head pose process. Several resultspresent the efficiency of the labelling process , particularlyits structural properties for the detection of heads within acrowd. A proposed method has been tested with an experimentof counting the number of pedestrians passing in aspecific area.

Learning articulated appearance models for tracking humans: A spectral graph matching approach

Tracking an unspecified number of people in real-time is one of the most challenging tasks in computer vision. In this paper, we propose an original method to achieve this goal, based on the construction of a 2D human appearance model. The general framework, which is a region-based tracking approach, is applicable to any type of object. We show how to specialize the method for taking advantage of the structural properties of the human body. We segment its visible parts by using a skeletal graph matching strategy inspired by the shock graphs. Only morphological and topological information is encoded in the model graph, making the approach independent of the pose of the person, the viewpoint, the geometry or the appearance of the limbs. The limbs labeling makes it possible to build and update an appearance model for each body part. The resulting discriminative feature, that we denote as an articulated appearance model, captures both color, texture and shape properties of the different limbs. It is used to identify people in complex situations (occlusion, field of view exit, etc.), and maintain the tracking. The model to image matching has proved to be much more robust and better-founded than with existing global appearance descriptors, specifically when dealing with highly deformable objects such as humans. The only assumption for the recognition is the approximate viewpoint correspondence between the different models during the matching process. The method does not make use of skin color detection, which allows us to perform tracking under any viewpoint. Occlusions can be detected by the generic part of the algorithm, and the tracking is performed in such cases by means of a particle filter. Several results in complex situations prove the capacity of the algorithm to learn people appearance in unspecified poses and viewpoints, and its efficiency for tracking multiple humans in real-time using the specific updated descriptors. Finally, the model provides an important clue for further human motion analysis process.

Human Body Part Labeling and Tracking Using Graph Matching Theory

Properly labeling human body parts in video sequences is essential for robust tracking and motion interpretation frameworks. We propose to perform this task by using Graph Matching. The silhouette skeleton is computed and decomposed into a set of segments corresponding to the different limbs. A Graph capturing the topology of the segments is generated and matched against a 3D model of the human skeleton. The limb identification is carried out for each node of the graph, potentially leading to the absence of correspondence. The method captures the minimal information about the skeleton shape. No assumption about the viewpoint, the human pose, the geometry or the appearance of the limbs is done during the matching process, making the approach applicable to every configuration. Some correspondences that might be ambiguous only relying on topology are enforced by tracking each graph node over time. Several results present the efficiency of the labeling, particularly its robustness to limb detection errors that are likely to occur in real situations because of occlusions or low level system failures. Finally the relevance of the labeling in an overall tracking system is described.

People re-identification across multiple non-overlapping cameras system by appearance classification and silhouette part segmentation

In this paper, we present a new person re-identification method based on appearance classification and silhouette part segmentation. In crowded areas, heads are considered as most apparent parts, hence the typical advantage of using the skeleton graph for the head detection and location of people after partial occlusion. The appearance classification consists in characterizing the appearance of a person into two classes, the frontal and the back appearance, using head detector and the orthogonal iteration algorithm for head pose estimation. The silhouette part segmentation divides the silhouette into three horizontal parts, ideally corresponding to head, torso and legs using skeleton graph and head detector. Our approach is robust to real world situations, in particular to variations in scales, human pose, illumination and clothes appearance changes. It also allows to reduce the confusion cases among people appearance and the amount of falsely matches.

Underwater image preprocessing for automated photogrammetry in high turbidity water: An application on the Arles-Rhone XIII roman wreck in the Rhodano river, France

ROV 3D project aims at developing innovative tools which link underwater photogrammetry and acoustic measurements from an active underwater sensor. The results will be 3D high resolution surveys of underwater sites. The new means and methods developed aim at reducing the investigation time in situ, and proposing comprehensive and non-intrusive measurement tools for the studied environment. In this paper, we apply a pre-processing pipe line to increase the SIFT and SURF descriptors extraction quality in order to solve the problem of surveying an underwater archaeological wreck in a very high condition of turbidity. We work in the Rhodano river, in south of France on a roman wreck with 20 centimeters visibility. Under these conditions a standard process is not efficient and water turbidity is a real obstacle to feature extraction. Nevertheless the mission was not dedicated to an exhaustive survey of the wreck, but only a test to show and evaluate the feasibility. The results are positive even if the main problem seems now to be the time processing, indeed the poor visibility increase drastically the number of photographs.

Harvesting effects, recovery mechanisms, and management strategies for a long-lived and structural precious coral.

Overexploitation is a major threat for the integrity of marine ecosystems. Understanding the ecological consequences of different extractive practices and the mechanisms underlying the recovery of populations is essential to ensure sustainable management plans. Precious corals are long-lived structural invertebrates, historically overfished, and their conservation is currently a worldwide concern. However, the processes underlying their recovery are poorly known. Here, we examined harvesting effects and recovery mechanisms of red coral Corallium rubrum by analyzing long-term photographic series taken on two populations that were harvested. We compared the relative importance of reproduction and re-growth as drivers of resilience. Harvesting heavily impacted coral populations causing large decreases in biomass and strong size-class distribution shifts towards populations dominated by small colonies. At the end of the study (after 4 and 7 years) only partial recovery was observed. The observed general pattern of low recruitment and high mortality of new recruits demonstrated limited effects of reproduction on population recovery. Adversely, low mortality of partially harvested adults and a large proportion of colonies showing new branches highlighted the importance of re-growth in the recovery process. The demographic projections obtained through stochastic models confirmed that the recovery rates of C. rubrum can be strongly modulated depending on harvesting procedures. Thus, leaving the basal section of the colonies when harvesting to avoid total mortality largely enhances the resilience of C. rubrum populations and quickens their recovery. On the other hand, the high survival of harvested colonies and the significant biomass reduction indicated that abundance may not be an adequate metric to assess the conservation status of clonal organisms because it can underestimate harvesting effects. This study highlights the unsustainability of current harvesting practices of C. rubrum and provides urgently needed data to improve management practices that are still largely based on untested assumptions.

Person re-identification using appearance classification

In this paper, we present a person re-identification method based on appearance classification. It consists a human silhouette comparison by characterizing and classification of a persons appearance (the front and the back appearance) using the geometric distance between the detected head of person and the camera. The combination of head detector with an orthogonal iteration algorithm to help head pose estimation and appearance classification is the novelty of our work. In this way, the is achieved robustness against viewpoint, illumination and clothes appearance changes. Our approach uses matching of interest-points descriptors based on fast cross-bin metric. The approach applies to situations where the number of people varies continuously, considering multiple images for each individual.

Underwater Photogrammetry for Archaeology. What Will Be the Next Step

Since 1973 archaeology and computer science have developed close ties in Marseille. Two departments (computer science and archaeology) from the French National Centre for Scientific Research (CNRS) in Marseille started working together and laid the cornerstone of the Computer Applications and Quantitative Methods in Archaeology (CAA) community. Marseille also has the advantage of being located in a very interesting place on the Mediterranean Sea and being the home to several famous laboratories, such as the French Cultural Heritage Department (DRASSM) or private companies like COMEX. In 1980 they performed a series of explorations of a deep-sea wreck with the help of COMEX and DRASSM. In this paper we present new advances in underwater photogrammetry for archaeology based on forty years of experience. The survey described in this article does not only discuss the acquisition of 3D points in difficult conditions but also linking archaeological knowledge to the surveyed geometry. This approach needed to com...

Eye gaze estimation from a video

Our work focuses on the interdisciplinary field of detailed analysis of behaviors exhibited by individuals during sessions of distributed collaboration. With a particular focus on ergonomics, we propose new mechanisms to be integrated into existing tools to enable increased productivity in distributed learning and working. Our technique is to record ocular movements (eye tracking) to analyze various scenarios of distributed collaboration in the context of computer-based training. In this article, we present a low-cost oculometric device that is capable of making ocular measurements without interfering with the natural behavior of the subject. We expect that this device could be employed anywhere that a natural, non-intrusive method of observation is required, and its low-cost permits it to be readily integrated into existing popular tools, particularly E-learning campus.

A regression-based method for the prediction of the indecisiveness degree through eye movement patterns

The development of eye-tracking-based methods to describe a persons indecisiveness is not commonly explored, even though research has shown that indecisiveness is involved in many unwanted cognitive states, such as a reduction in self-confidence during the decision-making process, doubts about past decisions, reconsidering, trepidation, distractibility, procrastination, neuroticism and even revenge. The purpose of our work is to propose a predictive model of a subjects degree of indecisiveness. To reach this goal, we first need to extract statistically relevant. Using eye-tracking methodology, we build a list of patterns that best distinguish decisive people from indecisive people; this segmentation is made according to the state of the art. The final list of eye-tracking patterns is also coherent with the state of art. A comparison between Multiple Linear Regression (MLR) and Support Vector Regression (SVR) is made so as to select the best predictive model.