Adaptive Object Detection Using Adjacency and Zoom Prediction

Lu, Yongxi; Javidi, Tara; Lazebnik, Svetlana

doi:10.48550/arxiv.1512.07711

Cited by 7 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method supports this more human-like approach of active object localization (e.g., [7], [15], [23]), in which a search for objects likewise unfolds over a series of time steps. At each time step the system uses information gained in previous time steps to decide where to search.…”

Section: Background and Related Worksupporting

confidence: 54%

Gaussian Processes with Context-Supported Priors for Active Object Localization

Rhodes

Witte²,

Mitchell

et al. 2018

2018 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

We devise an algorithm using a Bayesian optimization framework in conjunction with contextual visual data for the efficient localization of objects in still images. Recent research has demonstrated substantial progress in object localization and related tasks for computer vision. However, many current state-of-the-art object localization procedures still suffer from inaccuracy and inefficiency, in addition to failing to provide a principled and interpretable system amenable to high-level vision tasks. We address these issues with the current research.Our method encompasses an active search procedure that uses contextual data to generate initial bounding-box proposals for a target object. We train a convolutional neural network to approximate an offset distance from the target object. Next, we use a Gaussian Process to model this offset response signal over the search space of the target. We then employ a Bayesian active search for accurate localization of the target.In experiments, we compare our approach to a state-of-theart bounding-box regression method for a challenging pedestrian localization task. Our method exhibits a substantial improvement over this baseline regression method.

show abstract

Section: Background and Related Worksupporting

confidence: 54%

Gaussian Processes with Context-Supported Priors for Active Object Localization

Rhodes

Witte²,

Mitchell

et al. 2018

2018 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…Saudi Arabia has been looking for speedy inhabitants' development, progress, and automation, which's too, peaks to an excellent sort of solid waste. The nation's inhabitants were measured at 16.1 million in 1992, which expanded to 27.1 in 2010 [8,20]. In Saudi Arabia, community solid waste is disposed starting isolated or municipal containers and equipped of in landfills.…”

Section: Literature Reviewmentioning

confidence: 99%

“…YOLOv1, YOLOv2, and YOLOv3 have supported overall architecture of waste material an image, predefined broadcaster boxes to recover bounding box and object detection, transmission learning, and exercise original models from scratch [20].…”

Section: Yolo For Object Detection Technologymentioning

confidence: 99%

By the Population of Waste Materials Detection of Images in Smart Cities using Internet Drone

Dafallah Mohamed Alhasan,

Sharma,

Ben Said

et al. 2024

Interciencia

View full text Add to dashboard Cite

Internet drone, in modest things, is a kind of rapid automaton that is remotely organized by human beings. It is in machinery relations also known as Unmanned Floating Automobile (UFA). By numerous innovative developments in drone equipment, it has predictable that drones grow additional to contain analytical skills, specifically in the waste materials detection of images in smart cities. The drone offered in this article will be applied for the distribution of waste materials detection of images. Through a security system executed on the vessel involved, it confirms the protection of the waste materials detection of images till they get the correct place. The planned structure is an internet-based drone consuming the values of Internet of Things. Still, the procedure of drones’ desires trained control and appropriate setup. Waste materials detection of images by internet drone are misguidedly measured as security drones, therefore has been criticized by prepared services.

show abstract

“…Lu et al [28] improve localization by adaptively focusing on subregions likely to contain objects. Alexe et al [1] sequentially investigated locations based on what has been seen to improve detection accuracy.…”

Section: Related Workmentioning

confidence: 99%

Dynamic Zoom-in Network for Fast Object Detection in Large Images

Gao

Rong

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

140

View full text Add to dashboard Cite

We introduce a generic framework that reduces the computational cost of object detection while retaining accuracy for scenarios where objects with varied sizes appear in high resolution images. Detection progresses in a coarse-to-fine manner, first on a down-sampled version of the image and then on a sequence of higher resolution regions identified as likely to improve the detection accuracy. Built upon reinforcement learning, our approach consists of a model (Rnet) that uses coarse detection results to predict the potential accuracy gain for analyzing a region at a higher resolution and another model (Q-net) that sequentially selects regions to zoom in. Experiments on the Caltech Pedestrians dataset show that our approach reduces the number of processed pixels by over 50% without a drop in detection accuracy. The merits of our approach become more significant on a high resolution test set collected from YFCC100M dataset, where our approach maintains high detection performance while reducing the number of processed pixels by about 70% and the detection time by over 50%.

show abstract

Adaptive Object Detection Using Adjacency and Zoom Prediction

Cited by 7 publications

References 23 publications

Gaussian Processes with Context-Supported Priors for Active Object Localization

Gaussian Processes with Context-Supported Priors for Active Object Localization

By the Population of Waste Materials Detection of Images in Smart Cities using Internet Drone

Dynamic Zoom-in Network for Fast Object Detection in Large Images

Contact Info

Product

Resources

About