Bounding overwatch

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

Oriented Bounding Boxes for Small and Freely Rotated Objects

Abstract: A novel object detection method is presented that handles freely rotated objects of arbitrary sizes, including tiny objects as small as 2 x 2 pixels. Such tiny objects appear frequently in remotely sensed images, and present a challenge to recent object detection algorithms. More importantly, current object detection methods have been designed originally to accommodate axis-aligned bounding box detection, and therefore fail to accurately localize oriented boxes that best describe freely rotated objects. In contrast, the proposed convolutional neural network (CNN) -based approach uses potential pixel information at multiple scale levels without the need for any external resources, such as anchor boxes. The method encodes the precise location and orientation of features of the target objects at grid cell locations. Unlike existing methods that regress the bounding box location and dimension, the proposed method learns all the required information by classification, which has the added benefit of enabling oriented bounding box detection without any extra computation. It thus infers the bounding boxes only at inference time by finding the minimum surrounding box for every set of the same predicted class labels. Moreover, a rotation-invariant feature representation is applied to each scale, which imposes a regularization constraint to enforce covering the 360° range of in-plane rotation of the training samples to share similar features. Evaluations on the xView and dataset for object detection in aerial images (DOTA) data sets show that the proposed method uniformly improves performance over existing state-of-the-art methods.

Model quality in identification of nonlinear systems

Abstract: In this note, the problem of the quality of identified models of nonlinear systems, measured by the errors in simulating the system behavior for future inputs, is investigated. Models identified by classical methods minimizing the prediction error, do not necessary give "small" simulation error on future inputs and even boundedness of this error is not guaranteed. In order to investigate the simulation error boundedness (SEB) property of identified models, a Nonlinear Set Membership (NSM) method recently proposed by the authors is taken, assuming that the nonlinear regression function, representing the difference between the system to be identified and a linear approximation, has gradient norm bounded by a constant /spl gamma/. Moreover, the noise sequence is assumed unknown but bounded by a constant /spl epsiv/. The NSM method allows to obtain validation conditions, useful to derive "validated regions" within which to suitably choose the bounding constants /spl gamma/ and /spl epsiv/. Moreover, the method allows to derive an "optimal" estimate of the true system. If the chosen linear approximation is asymptotically stable (a necessary condition for the SEB property), in the present note a sufficient condition on /spl gamma/ is derived, guaranteeing that the identified optimal NSM model has the SEB property. If values of /spl gamma/ in the validated region exist, satisfying the sufficient condition, the previous results can be used to give guidelines for choosing the bounding constants /spl gamma/ and /spl epsiv/, additional to the ones required for assumptions validation and useful for obtaining models with "low" simulation errors. The numerical example, representing a mass-spring-damper system with nonlinear damper and input saturation, demonstrates the effectiveness of the presented approach.

UWB rapid-bit-exchange system for distance bounding

Abstract: Distance bounding protocols enable one device (the verifier) to securely establish an upper bound on its distance to another device (the prover). These protocols can be used for secure location verification and detection of relay attacks, even in presence of strong attackers. The rapid-bit-exchange is the core of distance bounding protocols---the verifier sends single bit challenges, which the prover is expected to answer with minimal and stable processing delay. Based on the measured round trip time of flight, the verifier calculates its upper bound to the prover. Although several aspects of distance bounding implementations have been discussed in the past, no full implementation of a wireless distance bounding system has been presented so far.In this work, we present the first full realization of a rapid bit exchange system for distance bounding. Our system consists of an Ultra-Wideband (UWB) ranging radio and of an efficient digital processing implemented on an Field-Programmable-Gate-Array (FPGA) board; it achieves a ranging accuracy of 7:5 cm and a short processing delay at the prover (

Dependence Measures Bounding the Exploration Bias for General Measurements

Abstract: We propose a framework to analyze and quantify the bias in adaptive data analysis. It generalizes that proposed by Russo and Zou'15, applying to measurements whose moment generating function exists, measurements with a finite $p$-norm, and measurements in general Orlicz spaces. We introduce a new class of dependence measures which retain key properties of mutual information while more effectively quantifying the exploration bias for heavy tailed distributions. We provide examples of cases where our bounds are nearly tight in situations where the original framework of Russo and Zou'15 does not apply.

An End-to-End Transformer Model for Crowd Localization

Abstract: Crowd localization, predicting head positions, is a more practical and high-level task than simply counting. Existing methods employ pseudo-bounding boxes or pre-designed localization maps, relying on complex post-processing to obtain the head positions. In this paper, we propose an elegant, end-to-end Crowd Localization TRansformer named CLTR that solves the task in the regression-based paradigm. The proposed method views the crowd localization as a direct set prediction problem, taking extracted features and trainable embeddings as input of the transformer-decoder. To reduce the ambiguous points and generate more reasonable matching results, we introduce a KMO-based Hungarian matcher, which adopts the nearby context as the auxiliary matching cost. Extensive experiments conducted on five datasets in various data settings show the effectiveness of our method. In particular, the proposed method achieves the best localization performance on the NWPU-Crowd, UCF-QNRF, and ShanghaiTech Part A datasets.