Christele Lecomte

Preceding car tracking using belief functions and a particle filter

This article presents a preceding car rear view tracking algorithm which utilizes a particle filter and belief function data fusion. Most of tracking applications resort to only one source of information, making the system dependent on the source reliability. To achieve more robust and longer tracking, multiple source data fusion is a solution. Belief functions are a powerful tool for data fusion. Using bridges between probability theory and belief function theory, data fusion information can be incorporated inside a particle filter. The efficiency of the proposed method is demonstrated on natural on-road sequences.

An application of the Sequential Monte Carlo to increase the accuracy of travel time estimation in urban areas

This paper presents an application of the Sequential Monte Carlo that will help to increase the accuracy of travel time estimations in our historical data. Our estimation filter is based on the Monte Carlo Method and was modeled in such a way as to be applicable to our new kind of data in order to estimate travel time per section of road. We took into consideration the delay time while changing the sections to symbolize the delay due to traffic lights or crossroads. We worked on an urban zone of Rouen, a French city, to evaluate our application. In this application, information is collected from a specific GPS system that warns drivers of the location of both fixed and mobile speed radars. Unlike the classical GPS system, this system is characterized by the data flow frequency where the GPS data is received from the probe vehicles at one minute intervals. After receiving the data we apply the map matching method in order to correct the GPS errors. Also, our geo-referencing system has special features; each road or section of road is formed by nodes and segments, and the intersection between each section is called a PUMAS points. The PUMAS Points are GPS coordinate points on a digital map which can be propagated or moved without cost, providing total flexibility to mesh a city or rural area. Over all the performance of the filter estimator is around 85% if we set our threshold at 50%.

Fast Color-Texture Discrimination: Application to Car Tracking

Visual tracking methods have been intensively contributed in the past decade. Promising results have been brought, leading to partial solution of the problem. However it is still utmost difficult to maintain track of an object for a long time, because some events can strongly disrupt the tracking procedures. Such events are occlusions, clutters, illumination changes, particular movements or pose changes. To overcome these challenging events and produce more reliable tracking algorithms, image data must be exploited through several aspects, that is to say through several cues : texture, color, shape or movement. But before being able to use these sources, one must make sure that each of these sources is reliable and non-redundant. In this article, we reckon that texture and color must be jointly processed, and we propose a new color-texture feature called weighted cooccurrence matrices. Using this feature within a particle filter, successful car tracking examples are proposed.

A lidar-based method for the detection and counting of Powered Two Wheelers

The safety of Powered Two Wheelers (PTWs) is important for public authorities and road administrators around the world. Official figures show that PTW represent only 2% of the total traffic on French roads, but as these figures are obtained by simply counting the number plates registered, they do not give a true picture of the PTWs on the road at any given moment. To date, there is no overall solution to this problem that uses a sensor capable of detecting PTWs and taking into consideration their interaction with the other vehicles on the road (for example: Inter-lane traffic, when PTWs move in between two lanes on a highway), and no state-of-the-art technical solutions can be adapted to measure this category of vehicle in traffic (unlike cars and trucks). The research work in this domain has therefore, not been greatly developed which is an issue of concern. In this paper we present a new method of detecting PTWs by using a single-plane lidar, named the Last Line Check (LLC) method. This method uses the energy of the last scan to extract the information. After extraction, a Support Vector Machine (SVM) is used for classification. The LLC method is tested in real time and gives interesting results with a high precision.

Detection and counting of Powered Two Wheelers by laser scanner in real time on urban expressway

The safety of Powered Two Wheelers (PTWs) is an issue of concern for public authorities and road administrators around the world. In 2011, the official figures show that the PTW is estimated to represent only 2% of the total traffic but represents 30% of the deaths on the roads in France. The ambiguity in the values is due to the fact that the PTWs are particularly difficult to detect because of their unknown interactions with the other vehicles on the road. To date, there is no overall definite solution to this problem that uses a single sensor to detect and count this category of vehicle in the traffic. In this paper we present a robust method for detecting and counting PTWs in real time and real traffic, named the Last Line Check (LLC) method. This method can adapt to the angle at which the laser scanner is tilted with respect to the road and can estimate the non-observed values in the data. We can obtain data with an accuracy, which eases the extraction process. After extraction, a Support Vector Machine (SVM) is used for classification of laser scanner data. The approach gives encouraging results even when the traffic moves at up to 130 km/h with a precision of 98.5%.

A new method for the detection of motorbikes by laser ragefinder

The safety of powered two wheelers (PTWs) is an important concern for public authorities and road administrators. In France, even though road safety has improved since 2002, the number of accidents involving PTWs is still high. If we look at the figures, PTWs represent only 1% of the traffic but 28% of the deaths on the road. This shows that the risk of getting killed on a motorbike is 24 times greater than in a car. Over the past few years, there has been a significant rise in the number of PTWs, but there is still a lack of information on this class of vehicle. It is, therefore, difficult to study the interactions of PTWs with other road users and with the road infrastructure. The state-of-the-art study conducted in 2009 showed that there is no technical solution as such that can be adapted to measure this category of vehicle in traffic (unlike cars and trucks), so research in this domain has not greatly advanced, which is an issue of concern. In this paper we propose using a rangefinder to detect PTWs in traffic, a new method that shows promising results.

Tracking objects in videos with texture features

In this article, we address the problem of object tracking in videos for multimedia applications. To produce a reliable and robust tracking algorithm, several visual characteristics of the target object must be examined. The different sources of information must be carefully chosen so as to select only the most informative ones. We argue that color and texture cues can be both quickly handled by cooccurrence matrices. Yet these matrices are too sensitive to illumination changes occurring in natural scenes. By adding weights, drawn from kernels centered on representative colors of the object, the feature can cope with this matter. We provide experimental result obtained from different kinds of natural scenes.

An automatic relevance feedback in image retrieval using belief functions

This paper proposes an automatic relevance feedback approach for content-based image retrieval using information fusion and without any user input. This method is proposed as an alternative of the simple ranking of result images. The idea consists to pass from a simple user selected query image to multi-images query in order to get more information about the query image type. Given a query image, the system first computes its feature vector to rank the images according to a well-chosen similarity measure. For each retrieved image, the degree of belief about the relevance is then assigned as a function of this measure. This degree of belief is then updated using an iterative process. At each iteration, we evaluate, for each retrieved image, the degree of relevance using the combination of belief functions associated to previously retrieved images. Then, each retrieved image is not found by the query image only but it is found by the query image and previously retrieved images too. Some experimental results will be proposed in this paper in order to demonstrate that the methodology improves the efficiency and accuracy of retrieval systems.