Bounding overwatch

About: Bounding overwatch is a research topic. Over the lifetime, 966 publications have been published within this topic receiving 15156 citations.

Operator Norm-Based Statistical Linearization to Bound the First Excursion Probability of Nonlinear Structures Subjected to Imprecise Stochastic Loading

Abstract: This paper presents a highly efficient approach for bounding the responses and probability of failure of nonlinear models subjected to imprecisely defined stochastic Gaussian loads. Typically, such computations involve solving a nested double-loop problem, where the propagation of the aleatory uncertainty has to be performed for each realization of the epistemic parameters. Apart from near-trivial cases, such computation is generally intractable without resorting to surrogate modeling schemes, especially in the context of performing nonlinear dynamical simulations. The recently introduced operator norm framework allows for breaking this double loop by determining those values of the epistemic uncertain parameters that produce bounds on the probability of failure a priori. However, the method in its current form is only applicable to linear models due to the adopted assumptions in the derivation of the involved operator norms. In this paper, the operator norm framework is extended and generalized by resorting to the statistical linearization methodology to account for nonlinear systems. Two case studies are included to demonstrate the validity and efficiency of the proposed approach.

Labels are Not Perfect: Inferring Spatial Uncertainty in Object Detection

Abstract: The availability of many real-world driving datasets is a key reason behind the recent progress of object detection algorithms in autonomous driving. However, there exist ambiguity or even failures in object labels due to error-prone annotation process or sensor observation noise. Current public object detection datasets only provide deterministic object labels without considering their inherent uncertainty, as does the common training process or evaluation metrics for object detectors. As a result, an in-depth evaluation among different object detection methods remains challenging, and the training process of object detectors is sub-optimal, especially in probabilistic object detection. In this work, we infer the uncertainty in bounding box labels from LiDAR point clouds based on a generative model, and define a new representation of the probabilistic bounding box through a spatial uncertainty distribution. Comprehensive experiments show that the proposed model reflects complex environmental noises in LiDAR perception and the label quality. Furthermore, we propose Jaccard IoU (JIoU) as a new evaluation metric that extends IoU by incorporating label uncertainty. We conduct an in-depth comparison among several LiDAR-based object detectors using the JIoU metric. Finally, we incorporate the proposed label uncertainty in a loss function to train a probabilistic object detector and to improve its detection accuracy. We verify our proposed methods on two public datasets (KITTI, Waymo), as well as on simulation data. Code is released at https://github.com/ ZiningWang/Inferring-Spatial-Uncertainty-in-Object-Detection.

Oriented Localization of Surgical Tools by Location Encoding

Abstract: Surgical tool localization is the foundation to a series of advanced surgical functions e.g. image guided surgical navigation. For precise scenarios like surgical tool localization, sophisticated tools and sensitive tissues can be quite close. This requires a higher localization accuracy than general object localization. And it is also meaningful to know the orientation of tools. To achieve these, this paper proposes a Compressive Sensing based Location Encoding scheme, which formulates the task of surgical tool localization in pixel space into a task of vector regression in encoding space. Furthermore with this scheme, the method is able to capture orientation of surgical tools rather than simply outputting horizontal bounding boxes. To prevent gradient vanishing, a novel back-propagation rule for sparse reconstruction is derived. The back-propagation rule is applicable to different implementations of sparse reconstruction and renders the entire network end-to-end trainable. Finally, the proposed approach gives more accurate bounding boxes as well as capturing the orientation of tools, and achieves state-of-the-art performance compared with 9 competitive both oriented and non-oriented localization methods on a mainstream surgical image dataset: m2cai16-tool-locations. A range of experiments support our claim that regression in CSLE space performs better than traditionally detecting bounding boxes in pixel space.

Magnitude Bounded Matrix Factorisation for Recommender Systems

Abstract: Low rank matrix factorisation is often used in recommender systems as a way of extracting latent features. When dealing with large and sparse datasets, traditional recommendation algorithms face the problem of acquiring large, unrestrained, fluctuating values over predictions especially for users/items with very few corresponding observations. Although the problem has been somewhat solved by imposing bounding constraints over its objectives, and/or over all entries to be within a fixed range, in terms of gaining better recommendations, these approaches have two major shortcomings that we aim to mitigate in this work: one is they can only deal with one pair of fixed bounds for all entries, and the other one is they are very time-consuming when applied on large scale recommender systems. In this paper, we propose a novel algorithm named Magnitude Bounded Matrix Factorisation (MBMF), which allows different bounds for individual users/items and performs very fast on large scale datasets. The key idea of our algorithm is to construct a model by constraining the magnitudes of each individual user/item feature vector. We achieve this by converting from the Cartesian to Spherical coordinate system with radii set as the corresponding magnitudes, which allows the above constrained optimisation problem to become an unconstrained one. The Stochastic Gradient Descent (SGD) method is then applied to solve the unconstrained task efficiently. Experiments on synthetic and real datasets demonstrate that in most cases the proposed MBMF is superior over all existing algorithms in terms of accuracy and time complexity.

Tackling Truncation Errors in CSL Model Checking through Bounding Semantics

Abstract: Model checking aims to give exact answers to queries about a model’s execution but, in probabilistic model checking, ensuring exact answers might be difficult. Numerical iterative methods are heavily used in probabilistic model checking and errors caused by truncation may affect correctness. To tackle truncation errors, we investigate the bounding semantics of continuous stochastic logic for Markov chains. We first focus on analyzing truncation errors for model-checking the time-bounded or unbounded Until operator and propose new algorithms to generate lower and upper bounds. Then, we study the bounding semantics for a subset of nested CSL formulas. We demonstrate result on two models.