Eric Cohen-Solal

Visual Surveillance in Retail Stores and in the Home

This paper presents an overview of video surveillance activities at Philips Research USA, which serves as a research arm of Philips Communications, Security and Imaging, a global leader in the design and manufacture of advanced automatic security systems. We concentrate on two application domains: professional security market, with emphasis on retail monitoring, and a low-cost, automated residential security. The main application for pan-tilt-zoom (PTZ) cameras is typically tracking of intruders throughout the facility. In addition, camera calibration is an important capability, because it allows geometric reasoning with respect to the floor plan as well as enhanced control of the camera. Another major component of our work concerns video content analysis, the detection of security related objects and events from video. The system typically processes video in real-time and can provide immediate alarms to alert the security operator. Relevant information is also stored in a database so that it can be efficiently retrieved later. The third and final topic discussed in the paper is a residential monitoring application, namely an intruder detection system. We describe detection of moving objects robust to changes in lighting and an object classification scheme based on radial-basis networks.

An ontology-based similarity measure for biomedical data - Application to radiology reports

BACKGROUND Determining similarity between two individual concepts or two sets of concepts extracted from a free text document is important for various aspects of biomedicine, for instance, to find prior clinical reports for a patient that are relevant to the current clinical context. Using simple concept matching techniques, such as lexicon based comparisons, is typically not sufficient to determine an accurate measure of similarity. METHODS In this study, we tested an enhancement to the standard document vector cosine similarity model in which ontological parent-child (is-a) relationships are exploited. For a given concept, we define a semantic vector consisting of all parent concepts and their corresponding weights as determined by the shortest distance between the concept and parent after accounting for all possible paths. Similarity between the two concepts is then determined by taking the cosine angle between the two corresponding vectors. To test the improvement over the non-semantic document vector cosine similarity model, we measured the similarity between groups of reports arising from similar clinical contexts, including anatomy and imaging procedure. We further applied the similarity metrics within a k-nearest-neighbor (k-NN) algorithm to classify reports based on their anatomical and procedure based groups. 2150 production CT radiology reports (952 abdomen reports and 1128 neuro reports) were used in testing with SNOMED CT, restricted to Body structure, Clinical finding and Procedure branches, as the reference ontology. RESULTS The semantic algorithm preferentially increased the intra-class similarity over the inter-class similarity, with a 0.07 and 0.08 mean increase in the neuro-neuro and abdomen-abdomen pairs versus a 0.04 mean increase in the neuro-abdomen pairs. Using leave-one-out cross-validation in which each document was iteratively used as a test sample while excluding it from the training data, the k-NN based classification accuracy was shown in all cases to be consistently higher with the semantics based measure compared with the non-semantic case. Moreover, the accuracy remained steady even as k value was increased - for the two anatomy related classes accuracy for k=41 was 93.1% with semantics compared to 86.7% without semantics. Similarly, for the eight imaging procedures related classes, accuracy (for k=41) with semantics was 63.8% compared to 60.2% without semantics. At the same k, accuracy improved significantly to 82.8% and 77.4% respectively when procedures were logically grouped together into four classes (such as ignoring contrast information in the imaging procedure description). Similar results were seen at other k-values. CONCLUSIONS The addition of semantic context into the document vector space model improves the ability of the cosine similarity to differentiate between radiology reports of different anatomical and image procedure-based classes. This effect can be leveraged for document classification tasks, which suggests its potential applicability for biomedical information retrieval.

A computer vision system for on-screen item selection by finger pointing

Pointing at planar surfaces such as TV and computer monitors or projection screens can be a useful mode of interaction between humans and machines. To a large extent what seems to hinder the use of vision in such practical applications is the difficulty of the computational task, which is typically defined as 3-D reconstruction from uncalibrated 2-D images of a non-static scene. We describe below two designs where, using one or two cameras, the target of pointing on a flat monitor or screen is identified without 3-D inference, using only image morphing and line intersection. This is accomplished by registering the images with the target plane. When used to identify a pointing target on a surface hidden from the camera (e.g., a computer monitor which supports the camera itself as in most PC configurations), we add aperture(s) coplanar with the target surface in front of the camera(s). We describe experimental results showing a fully automated procedure for pointing target detection with high accuracy. The simplicity of our method and its robustness, as well as the relative accuracy of our results, can make pointing a practical means of human-machine interaction.

An Automated Carotid Pulse Assessment Approach Using Doppler Ultrasound

During cardiac arrest emergencies, lay rescuers are required to manually check the patients carotid pulse after the delivery of defibrillation shocks to assess the cardiac resuscitation progress of the patient. As a more automated way of monitoring the resuscitation progress, a new Doppler-ultrasound-based carotid pulse assessment approach is presented in this paper. The method works by analyzing the temporal aperiodicity of Doppler shifts seen in the ultrasound echoes returned from the patients carotid arteries. As a quantitative investigation with this method, we derived a new measure called the pulselessness indicator to assess whether a carotid pulse is absent based on the given Doppler information. To study the performance of the new carotid pulse checking method, we built a multi-channel CW Doppler prototype device to acquire Doppler data in vivo during cardiac arrest experiments conducted on five different swines and computed pulselessness indicator estimates with these data. Our results indicated that the Doppler-based pulse checking approach has good sensitivity and specificity: it had a pulselessness detection rate greater than 0.9 for a given false alarm rate of 0.05. As a further analysis, the prototype device was applied to other experiments where the swine had suffered cardiac arrest for over five minutes. It showed a consistent assessment performance on the monitoring of the swines resuscitation progress after defibrillation and chest compressions.

Mapping Institution-Specific Study Descriptions to RadLex Playbook Entries

The naming of imaging procedures is currently not standardized across institutions. As a result, it is a challenge to establish national registries, for instance, a national registry of dose to facilitate comparisons among different types of CT procedures. RSNA’s RadLex Playbook is an effort towards addressing this gap (by introducing a unique Playbook identifier called an RPID for each procedure), and the current research focuses on semi-automatically mapping institution-specific procedure descriptions to Playbook entries to assist with this standardization effort. We discuss an algorithm we have developed to facilitate the mapping process which first extracts RadLex codes from the procedure description and then uses the definition of an RPID to determine the most suitable RPID(s) for the extracted set of RadLex codes. We also developed a tool that has three modes of operations—a single procedure mapping mode that allows a user to map a single institution-specific procedure description to a Playbook entry, a bulk mode to process large number of descriptions, and an exploratory mode that assists a user to better understand how the selection of values for various Playbook attributes affects the resulting RPID. We validate our algorithms using 166 production CT procedure descriptions and discuss how the tool can be used by administrators to map institution-specific procedure descriptions to RPIDs.

A novel hands-free carotid ultrasound detects low-flow cardiac output in a swine model of pulseless electrical activity arrest

OBJECTIVE To determine if a hands-free, noninvasive Doppler ultrasound device can reliably detect low-flow cardiac output by measuring carotid artery blood flow velocities. We compared the ability of observers to detect carotid artery flow velocity differences between pseudo-pulseless electrical activity (PEA) and true-PEA cardiac arrest. METHODS Five swine were instrumented with aortic (Ao) and right atrial pressure-transducing catheters. The Doppler ultrasound device was adhered to the neck over the carotid artery. Continuous electrocardiogram, pressure readings, and Doppler signal were recorded. Each swine underwent multiple episodes of fibrillation and resuscitation. Episodes of true-PEA and pseudo-PEA were retrospectively identified from all resuscitation attempts by examination of electrocardiogram and Ao waveforms. The sensitivity and specificity of the device to detect pseudo-PEA was obtained using observers blinded to Ao waveform recordings. RESULTS There was good interobserver reliability related to identification of pseudo- and true-PEA (κ = 0.873). The observers blinded to Ao waveform recordings agreed on 8 of the 9 episodes of pseudo-PEA, whereas 4 false positives of 26 true-PEA events were reported (sensitivity, 0.89; specificity, 0.85). The Doppler device was able to detect carotid flow velocity over a wide range of Ao blood pressures. CONCLUSIONS This hands-free, noninvasive Doppler ultrasound device can reliably differentiate pseudo-PEA from true-PEA during resuscitation from cardiac arrest, detecting pressure gradient changes of less than 5 mm Hg through to normotension. This device distinguishes conditions of no cardiac output from low cardiac output and may have applications for use during resuscitation from various etiologies of arrest and shock.

Real time skin-region detection with a single-chip digital camera

This article describes a 30 frames/second VGA format image sensor made in a standard CMOS process with an embedded massively parallel processor. The processor is fully programmable and therefore the sensor IC itself is able to run a variety of algorithms with data and processing in close vicinity of the sensor. Because of the parallel architecture comprising processor array and parallel memory accesses, high computational performances of up to 5 GOPS at 16 MHz are achieved. This high performance allowed us to implement skin tone detection on the camera itself as part of a larger system for face recognition, releasing the host computer of cumbersome pixel processing tasks and minimizing the data transfer between camera and computer.