Applying crash data to injury claims - an investigation of determinant factors in severe motor vehicle accidents.

An extensive number of research studies have attempted to capture the factors that influence the severity of vehicle impacts. The high number of risks facing all traffic participants has led to a gradual increase in sophisticated data collection schemes linking crash characteristics to subsequent severity measures. This study serves as a departure from previous research by relating injuries suffered in road traffic accidents to expected trauma compensation payouts and deriving a quantitative cost function. Data from the National Highway Traffic Safety Administration's (NHTSA) Crash Injury Research (CIREN) database for the years 2005-2014 is combined with the Book of Quantum, an Irish governmental document that offers guidelines on the appropriate compensation to be awarded for injuries sustained in accidents. A multiple linear regression is carried out to identify the crash factors that significantly influence expected compensation costs and compared to ordered and multinomial logit models. The model offers encouraging results given the inherent variation expected in vehicular incidents and the subjectivity influencing compensation payout judgments, attaining an adjusted-R2 fit of 20.6% when uninfluential factors are removed. It is found that relative speed at time of impact and dark conditions increase the expected costs, while rear-end incidents, incident sustained in van-based trucks and incidents sustained while turning result in lower expected compensations. The number of airbags available in the vehicle is also a significant factor. The scalar-outcome approach used in this research offers an alternative methodology to the discrete-outcome models that dominate traffic safety analyses. The results also raise queries on the future development of claims reserving (capital allocations earmarked for future expected claims payments) as advanced driver assistant systems (ADASs) seek to eradicate the most frequent types of crash factors upon which insurance mathematics base their assumptions.

Toward Self-Referential Autonomous Learning of Object and Situation Models.

Most current approaches to scene understanding lack the capability to adapt object and situation models to behavioral needs not anticipated by the human system designer. Here, we give a detailed description of a system architecture for self-referential autonomous learning which enables the refinement of object and situation models during operation in order to optimize behavior. This includes structural learning of hierarchical models for situations and behaviors that is triggered by a mismatch between expected and actual action outcome. Besides proposing architectural concepts, we also describe a first implementation of our system within a simulated traffic scenario to demonstrate the feasibility of our approach.

Dynamic, Task-Related and Demand-Driven Scene Representation.

Humans selectively process and store details about the vicinity based on their knowledge about the scene, the world and their current task. In doing so, only those pieces of information are extracted from the visual scene that is required for solving a given task. In this paper, we present a flexible system architecture along with a control mechanism that allows for a task-dependent representation of a visual scene. Contrary to existing approaches, our system is able to acquire information selectively according to the demands of the given task and based on the system's knowledge. The proposed control mechanism decides which properties need to be extracted and how the independent processing modules should be combined, based on the knowledge stored in the system's long-term memory. Additionally, it ensures that algorithmic dependencies between processing modules are resolved automatically, utilizing procedural knowledge which is also stored in the long-term memory. By evaluating a proof-of-concept implementation on a real-world table scene, we show that, while solving the given task, the amount of data processed and stored by the system is considerably lower compared to processing regimes used in state-of-the-art systems. Furthermore, our system only acquires and stores the minimal set of information that is relevant for solving the given task.

Estimating object proper motion using optical flow, kinematics, and depth information.

For the interaction of a mobile robot with a dynamic environment, the estimation of object motion is desired while the robot is walking and/or turning its head. In this paper, we describe a system which manages this task by combining depth from a stereo camera and computation of the camera movement from robot kinematics in order to stabilize the camera images. Moving objects are detected by applying optical flow to the stabilized images followed by a filtering method, which incorporates both prior knowledge about the accuracy of the measurement and the uncertainties of the measurement process itself. The efficiency of this system is demonstrated in a dynamic real-world scenario with a walking humanoid robot.

A probabilistic model for binaural sound localization.

This paper proposes a biologically inspired and technically implemented sound localization system to robustly estimate the position of a sound source in the frontal azimuthal half-plane. For localization, binaural cues are extracted using cochleagrams generated by a cochlear model that serve as input to the system. The basic idea of the model is to separately measure interaural time differences and interaural level differences for a number of frequencies and process these measurements as a whole. This leads to two-dimensional frequency versus time-delay representations of binaural cues, so-called activity maps. A probabilistic evaluation is presented to estimate the position of a sound source over time based on these activity maps. Learned reference maps for different azimuthal positions are integrated into the computation to gain time-dependent discrete conditional probabilities. At every timestep these probabilities are combined over frequencies and binaural cues to estimate the sound source position. In addition, they are propagated over time to improve position estimation. This leads to a system that is able to localize audible signals, for example human speech signals, even in reverberating environments.

Non-Gaussian velocity distributions integrated over space, time, and scales.

Velocity distributions are an enhanced representation of image velocity containing more velocity information than velocity vectors. In particular, non-Gaussian velocity distributions allow for the representation of ambiguous motion information caused by the aperture problem or multiple motions at motion boundaries. To resolve motion ambiguities, discrete non-Gaussian velocity distributions are suggested, which are integrated over space, time, and scales using a joint Bayesian prediction and refinement approach. This leads to a hierarchical velocity-distribution representation from which robust velocity estimates for both slow and high speeds as well as statistical confidence measures rating the velocity estimates can be computed.

Learning viewpoint invariant object representations using a temporal coherence principle.

Invariant object recognition is arguably one of the major challenges for contemporary machine vision systems. In contrast, the mammalian visual system performs this task virtually effortlessly. How can we exploit our knowledge on the biological system to improve artificial systems? Our understanding of the mammalian early visual system has been augmented by the discovery that general coding principles could explain many aspects of neuronal response properties. How can such schemes be transferred to system level performance? In the present study we train cells on a particular variant of the general principle of temporal coherence, the "stability" objective. These cells are trained on unlabeled real-world images without a teaching signal. We show that after training, the cells form a representation that is largely independent of the viewpoint from which the stimulus is looked at. This finding includes generalization to previously unseen viewpoints. The achieved representation is better suited for view-point invariant object classification than the cells' input patterns. This property to facilitate view-point invariant classification is maintained even if training and classification take place in the presence of an--also unlabeled--distractor object. In summary, here we show that unsupervised learning using a general coding principle facilitates the classification of real-world objects, that are not segmented from the background and undergo complex, non-isomorphic, transformations.