scispace - formally typeset
Search or ask a question
Topic

Bounding overwatch

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


Papers
More filters
Journal ArticleDOI
TL;DR: A Reposition Non-Maximum Suppression (R-NMS) algorithm is further proposed in post-processing to improve the localization accuracy of the optimal bounding boxes, and a Bi-directional Path Aggregation Network (BiPANet) is presented to fuse low-resolution feature maps with strong semantic information and high-resolutionfeature maps with detailed information.
Abstract: This study proposes a novel lightweight grape detection method. First, the backbone network of our method is Uniformer, which captures long-range dependencies and further improves the feature extraction capability. Then, a Bi-directional Path Aggregation Network (BiPANet) is presented to fuse low-resolution feature maps with strong semantic information and high-resolution feature maps with detailed information. BiPANet is constructed by introducing a novel cross-layer feature enhancement strategy into the Path Aggregation Network, which fuses more feature information with a significant reduction in the number of parameters and computational complexity. To improve the localization accuracy of the optimal bounding boxes, a Reposition Non-Maximum Suppression (R-NMS) algorithm is further proposed in post-processing. The algorithm performs repositioning operations on the optimal bounding boxes by using the position information of the bounding boxes around the optimal bounding boxes. Experiments on the WGISD show that our method achieves 87.7% mAP, 88.6% precision, 78.3% recall, 83.1% F1 score, and 46 FPS. Compared with YOLOx, YOLOv4, YOLOv3, Faster R-CNN, SSD, and RetinaNet, the mAP of our method is increased by 0.8%, 1.7%, 3.5%, 21.4%, 2.5%, and 13.3%, respectively, and the FPS of our method is increased by 2, 8, 2, 26, 0, and 10, respectively. Similar conclusions can be obtained on another grape dataset. Encouraging experimental results show that our method can achieve better performance than other recognized detection methods in the grape detection tasks.

4 citations

Journal ArticleDOI
TL;DR: In this article , the authors proposed a method that effectively captures subtle changes by aggregating context-aware features from most relevant image-regions and their importance in discriminating fine-grained categories avoiding the bounding box and/or distinguishable part annotations.
Abstract: Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts information from texture and shape. This is often inappropriate for fine-grained visual classification (FGVC) since it exhibits high intra-class and low inter-class variances due to occlusions, deformation, illuminations, etc. Thus, an expressive feature representation describing global structural information is a key to characterize an object/ scene. To this end, we propose a method that effectively captures subtle changes by aggregating context-aware features from most relevant image-regions and their importance in discriminating fine-grained categories avoiding the bounding-box and/or distinguishable part annotations. Our approach is inspired by the recent advancement in self-attention and graph neural networks (GNNs) approaches to include a simple yet effective relation-aware feature transformation and its refinement using a context-aware attention mechanism to boost the discriminability of the transformed feature in an end-to-end learning process. Our model is evaluated on eight benchmark datasets consisting of fine-grained objects and human-object interactions. It outperforms the state-of-the-art approaches by a significant margin in recognition accuracy.

4 citations

Proceedings ArticleDOI
16 Dec 1998
TL;DR: It is shown that using the matrix-based bounding has some advantages in the consideration of the global optimization for MPEP over the element-wise bounding.
Abstract: In this paper, we compare the matrix-based bounding and the element-wise bounding concerning the global optimization for the matrix product eigenvalues problem (MPEP), which addresses many typical bilinear matrix inequality problems for control synthesis. It is shown that using the matrix-based bounding has some advantages in the consideration of the global optimization for MPEP over the element-wise bounding. Numerical experiments illustrate that the algorithm using the matrix-based bounding is better than that of the element-wise bounding in the total computational time.

4 citations

Book ChapterDOI
19 Feb 2017
TL;DR: DBID approach provides a natural way of modelling man-in-the-middle attack in line with identification protocols, as well as other attacks that are commonly considered in distance bounding protocols.
Abstract: Distance bounding (DB) protocols allow a prover to convince a verifier that they are within a distance bound. A public key distance bounding relies on the public key of the users to prove their identity and proximity claim. There has been a number of approaches in the literature to formalize security of public key distance bounding protocols. In this paper we extend an earlier work that formalizes security of public key DB protocols using an approach that is inspired by the security definition of identification protocols, and is referred to it as distance-bounding identification (\(\mathtt {DBID}\)). We first show that if protocol participants have access to a directional antenna, many existing protocols that have been proven secure, will become insecure, and then show to revise the previous model to include this new capability of the users. DBID approach provides a natural way of modelling man-in-the-middle attack in line with identification protocols, as well as other attacks that are commonly considered in distance bounding protocols. We compare the existing public key DB models, and prove the security of the scheme known as \(\mathtt {ProProx}\), in our model.

4 citations

Posted Content
TL;DR: In this article, the authors present an efficient algorithmic framework for constructing multi-level hp-bases that uses a data-oriented approach that easily extends to any number of dimensions and provides a natural framework for performance-optimized implementations.
Abstract: We present an efficient algorithmic framework for constructing multi-level hp-bases that uses a data-oriented approach that easily extends to any number of dimensions and provides a natural framework for performance-optimized implementations. We only operate on the bounding faces of finite elements without considering their lower-dimensional topological features and demonstrate the potential of the presented methods using a newly written open-source library. First, we analyze a Fichera corner and show that the framework does not increase runtime and memory consumption when compared against the classical p-version of the finite element method. Then, we compute a transient example with dynamic refinement and derefinement, where we also obtain the expected convergence rates and excellent performance in computing time and memory usage.

4 citations


Network Information
Related Topics (5)
Robustness (computer science)
94.7K papers, 1.6M citations
85% related
Optimization problem
96.4K papers, 2.1M citations
85% related
Matrix (mathematics)
105.5K papers, 1.9M citations
82% related
Nonlinear system
208.1K papers, 4M citations
81% related
Artificial neural network
207K papers, 4.5M citations
80% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023714
20221,629
2021155
202075
201973
201850