Bounding overwatch

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

F2DNet: Fast Focal Detection Network for Pedestrian Detection

Abstract: Two-stage detectors are state-of-the-art in object detection as well as pedestrian detection. However, the current two-stage detectors are inefficient as they do bounding box regression in multiple steps i.e. in region proposal networks and bounding box heads. Also, the anchor-based region proposal networks are computationally expensive to train. We propose F2DNet, a novel two-stage detection architecture which eliminates redundancy of current two-stage detectors by replacing the region proposal network with our focal detection network and bounding box head with our fast suppression head. We benchmark F2DNet on top pedestrian detection datasets, thoroughly compare it against the existing state-of-the-art detectors and conduct cross dataset evaluation to test the generalizability of our model to unseen data. Our F2DNet achieves 8.7%, 2.2%, and 6.1% MR ² on City Persons, Caltech Pedestrian, and Euro City Person datasets respectively when trained on a single dataset and reaches 20.4% and 26.2% MR ² in heavy occlusion setting of Caltech Pedestrian and City Persons datasets when using progressive fine-tunning. Furthermore, F2DNet have significantly lesser inference time compared to the current state-of-the-art. Code and trained models will be available at https://github.com/AbdulHannanKhan/F2DNet.

Unfolding-Aided Bootstrapped Phase Retrieval in Optical Imaging: Explainable AI reveals new imaging frontiers

Abstract: Phase retrieval in optical imaging refers to the recovery of a complex signal from phaseless data acquired in the form of its diffraction patterns. These patterns are acquired through a system with a coherent light source that employs a diffractive optical element (DOE) to modulate the scene, resulting in coded diffraction patterns (CDPs) at the sensor. Recently, the hybrid approach of a model-driven network or deep unfolding has emerged as an effective alternative to conventional model- and learning-based phase-retrieval techniques because it allows for bounding the complexity of algorithms while also retaining their efficacy. Additionally, such hybrid approaches have shown promise in improving the design of DOEs that follow theoretical uniqueness conditions. There are opportunities to exploit novel experimental setups and resolve even more complex DOE phase-retrieval applications. This article presents an overview of algorithms and applications of deep unfolding for bootstrapped—regardless whether near, middle, or far zones—phase retrieval.

Target-Aware State Estimation for Visual Tracking

Abstract: Trackers based on the IoU prediction network (IoU-Net) have shown superior performance, which refines a coarse bounding box to an accurate one by maximizing the IoU between the target and the coarse box. However, the traditional IoU-Net is less effective in exploiting the limited but crucial supervision information contained in the initial frame, including the discriminative information between the target and backgrounds and the structure information of the initial target. Missing such information makes the IoU-Net less robust to background distractors and diverse variations of the target appearance. To address this issue, we propose a target-aware state estimation network for visual tracking. A gradient-guided feature adjustment module is built on an online discriminative model to generate target-aware features for constructing the state estimation network; it conveys the online learned discriminative information into the offline trained state estimation network. In addition, we propose a structure-aware integration module and embed it into the state estimation network, enabling the tracker to explicitly model the structure information of the initial target. Extensive experimental results on the VOT2018, OTB2015, UAV123, NFS30, TC128, TrackingNet, LaSOT, and VOT2018-LT datasets demonstrate that the proposed approach performs favorably against state-of-the-art trackers.

Systematic search for extreme and singular behaviour in some fundamental models of fluid mechanics

Abstract: This review article offers a survey of the research program focused on a systematic computational search for extreme and potentially singular behaviour in hydrodynamic models motivated by open questions concerning the possibility of a finite-time blow-up in the solutions of the Navier-Stokes system. Inspired by the seminal work of Lu & Doering (2008 Ind. Univ. Math.57, 2693-2727), we sought such extreme behaviour by solving PDE optimization problems with objective functionals chosen based on certain conditional regularity results and a priori estimates available for different models. No evidence for singularity formation was found in extreme Navier-Stokes flows constructed in this manner in three dimensions. We also discuss the results obtained for one-dimensional Burgers and two-dimensional Navier-Stokes systems, and while singularities are ruled out in these flows, the results presented provide interesting insights about sharpness of different energy-type estimates known for these systems. Connections to other bounding techniques are also briefly discussed. This article is part of the theme issue 'Mathematical problems in physical fluid dynamics (part 1)'.