No abstract

Using multiple sensors in the context of environment perception for autonomous vehicles is quite common these days. Perceived data from these sensors can be fused at different levels like: before object detection, after object detection and finally after tracking the moving objects. In this paper we detail our object detection level fusion between laser and stereo vision sensors as opposed to pre-detection or track level fusion. We use the output of our laser processing to get a list of objects with position and dynamic properties for each object. Similarly we use the stereo vision output of another team which consists of a list of detected objects with position and classification properties for each object. We use Bayesian fusion technique on objects of these two lists to get a new list of fused objects. This fused list of objects is further used in tracking phase to track moving objects in an intersection like scenario. The results obtained on data sets of INTERSAFE-2 demonstrator vehicle show that this fusion has improved data association and track management steps.

No abstract

Histopathological image analysis is a challenging task due to a diverse histology feature set as well as due to the presence of large non-informative regions in whole slide images. In this paper, we propose a multiple-instance learning (MIL) method for image-level classification as well as for annotating relevant regions in the image. In MIL, a common assumption is that negative bags contain only negative instances while positive bags contain one or more positive instances. This asymmetric assumption may be inappropriate for some application scenarios where negative bags also contain representative negative instances. We introduce a novel symmetric MIL framework associating each instance in a bag with an attribute which can be either negative, positive, or irrelevant. We extend the notion of relevance by introducing control over the number of relevant instances. We develop a probabilistic graphical model that incorporates the aforementioned paradigm and a corresponding computationally efficient inference for learning the model parameters and obtaining an instance level attribute-learning classifier. The effectiveness of the proposed method is evaluated on available histopathology datasets with promising results.

Abstract-Intelligent vehicle perception involves the correct detection and tracking of moving objects. Taking into account all the possible information at early levels of the perception task can improve the final model of the environment. In this paper, we present an evidential fusion framework to represent and combine evidence from multiple lists of sensor detections. Our fusion framework considers the position, shape and appearance information to represent, associate and combine sensor detections. Although our approach takes place at detection level, we propose a general architecture to include it as a part of a whole perception solution. Several experiments were conducted using real data from a vehicle demonstrator equipped with three main sensors: lidar, radar and camera. The obtained results show improvements regarding the reduction of false detections and mis-classifications of moving objects.

Abstract-In this paper, we present a vehicle safety application based on data gathered by a laser scanner and two short range radars that recognizes unavoidable collisions with stationary objects before they take place in order to trigger restraint systems. Two different software modules are compared that perform the processing of raw data and deliver a description of the vehicle's environment. A comprehensive experimental evaluation based on relevant crash and non-crash scenarios is presented.

No abstract

Factorization-based gradient descent is a scalable and efficient algorithm for solving low-rank matrix completion. Recent progress in structured non-convex optimization has offered global convergence guarantees for gradient descent under certain statistical assumptions on the low-rank matrix and the sampling set. However, while the theory suggests gradient descent enjoys fast linear convergence to a global solution of the problem, the universal nature of the bounding technique prevents it from obtaining an accurate estimate of the rate of convergence. This paper performs a local analysis of the exact linear convergence rate of gradient descent for factorization-based symmetric matrix completion. Without any additional assumptions on the underlying model, we identify the deterministic condition for local convergence guarantee for gradient descent, which depends only on the solution matrix and the sampling set. More crucially, our analysis provides a closed-form expression of the asymptotic rate of convergence that matches exactly with the linear convergence observed in practice. To the best of our knowledge, our result is the first one that offers the exact linear convergence rate of gradient descent for matrix factorization in Euclidean space for matrix completion.