Bounding overwatch

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

Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation

Abstract: Weakly supervised semantic segmentation is receiving great attention due to its low human annotation cost. In this paper, we aim to tackle bounding box supervised semantic segmentation, i.e., training accurate semantic segmentation models using bounding box annotations as supervision. To this end, we propose affinity attention graph neural network ( A2GNN). Following previous practices, we first generate pseudo semantic-aware seeds, which are then formed into semantic graphs based on our newly proposed affinity Convolutional Neural Network (CNN). Then the built graphs are input to our A2GNN, in which an affinity attention layer is designed to acquire the short- and long- distance information from soft graph edges to accurately propagate semantic labels from the confident seeds to the unlabeled pixels. However, to guarantee the precision of the seeds, we only adopt a limited number of confident pixel seed labels for A2GNN, which may lead to insufficient supervision for training. To alleviate this issue, we further introduce a new loss function and a consistency-checking mechanism to leverage the bounding box constraint, so that more reliable guidance can be included for the model optimization. Experiments show that our approach achieves new state-of-the-art performances on Pascal VOC 2012 datasets (val: 76.5 percent, test: 75.2 percent). More importantly, our approach can be readily applied to bounding box supervised instance segmentation task or other weakly supervised semantic segmentation tasks, with state-of-the-art or comparable performance among almot all weakly supervised tasks on PASCAL VOC or COCO dataset. Our source code will be available at https://github.com/zbf1991/A2GNN.

Document page decomposition using bounding boxes of connected components of black pixels

Abstract: Segmentation of document images can be performed by projecting image pixels. This pixel projection approach is one of widely used top-down segmentation methods and is based on the assumption that the document image has been correctly deskewed. Unfortunately, the pixel projection approach is computationally inefficient. It is because each symbol is not treated as a computational unit. In this paper, we explain a new technique which is highly tactical in the profiling analysis. Instead of projecting image pixels, we first compute the bounding box of each connected component in a document image and then we project those bounding boxes. Using the new technique, this paper describes how to extract words, text lines, and text blocks (e.g., paragraphs). This bounding box projection approach has many advantages over the pixel projection approach. It is less computationally involved. When applied to text zones, it is also possible to infer from the projection profiles how bounding boxes (and, therefore, primitive symbols) are aligned and/or where significant horizontal and vertical gaps are present. Since the new technique manipulates only bounding boxes, it can be applied to any noncursive language documents.

Modelling and Analysis of a Hierarchy of Distance Bounding Attacks

Abstract: We present an extension of the applied pi-calculus that can be used to model distance bounding protocols. A range of different security properties have been suggested for distance bounding protocols; we show how these can be encoded in our model and prove a partial order between them. We also relate the different security properties to particular attacker models. In doing so, we identify a new property, which we call uncompromised distance bounding, that captures the attacker model for protecting devices such as contactless payment cards or car entry systems, which assumes that the prover being tested has not been compromised, though other provers may have been. We show how to compile our new calculus into the applied pi-calculus so that protocols can be automatically checked with the ProVerif tool and we use this to analyse distance bounding protocols from MasterCard and NXP.

OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication

Abstract: Employing Vehicle-to-Vehicle communication to enhance perception performance in self-driving technology has attracted considerable attention recently; however, the absence of a suitable open dataset for benchmarking algorithms has made it difficult to develop and assess cooperative perception technologies. To this end, we present the first large-scale open simulated dataset for Vehicle-to-Vehicle perception. It contains over 70 interesting scenes, 11,464 frames, and 232,913 annotated 3D vehicle bounding boxes, collected from 8 towns in CARLA and a digital town of Culver City, Los Angeles. We then construct a comprehensive benchmark with a total of 16 implemented models to evaluate several information fusion strategies~(i.e. early, late, and intermediate fusion) with state-of-the-art LiDAR detection algorithms. Moreover, we propose a new Attentive Intermediate Fusion pipeline to aggregate information from multiple connected vehicles. Our experiments show that the proposed pipeline can be easily integrated with existing 3D LiDAR detectors and achieve outstanding performance even with large compression rates. To encourage more researchers to investigate Vehicle-to-Vehicle perception, we will release the dataset, benchmark methods, and all related codes in https://mobility-lab.seas.ucla.edu/opv2v/.