Model generation for video-based object recognition

Noor, Humera; Mirza, Shakeel Ahmed; Sheikh, Yaser; Jain, Amit; Shah, Mubarak

doi:10.1145/1180639.1180791

Cited by 12 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 14 ], the underlying topological structure of an image dataset was generated as a neighborhood graph of features. Motion continuity in the query video was exploited to demonstrate that the results obtained using a video, compared to results obtained using a single image, are more robust albeit more intensive computationally.…”

Section: Related Papersmentioning

confidence: 99%

Lightweight Active Object Retrieval with Weak Classifiers

Czúni

Rashad

2018

Sensors

View full text Add to dashboard Cite

In the last few years, there has been a steadily growing interest in autonomous vehicles and robotic systems. While many of these agents are expected to have limited resources, these systems should be able to dynamically interact with other objects in their environment. We present an approach where lightweight sensory and processing techniques, requiring very limited memory and processing power, can be successfully applied to the task of object retrieval using sensors of different modalities. We use the Hough framework to fuse optical and orientation information of the different views of the objects. In the presented spatio-temporal perception technique, we apply active vision, where, based on the analysis of initial measurements, the direction of the next view is determined to increase the hit-rate of retrieval. The performance of the proposed methods is shown on three datasets loaded with heavy noise.

show abstract

Section: Related Papersmentioning

confidence: 99%

Lightweight Active Object Retrieval with Weak Classifiers

Czúni

Rashad

2018

Sensors

View full text Add to dashboard Cite

show abstract

“…To achieve robust object recognition from images and videos, several approaches have been proposed [20,7,22] to exploit object appearance and geometrical information. Meantime, object detection has made tremendous progress over past years in various directions: real-time deformable object detection [24] and application of geometric scene context for detection [9].…”

Section: Related Workmentioning

confidence: 99%

Object fingerprints for content analysis with applications to street landmark localization

Yang

2008

Proceedings of the 16th ACM International Conference on Multimedia

View full text Add to dashboard Cite

An object can be a basic unit for multimedia content analysis. Besides similarity among common objects, each object has its own unique characteristics which we cannot find in other surrounding objects in multimedia data. We call such unique characteristics object fingerprints. In this paper, we propose a novel approach to extract and match object fingerprints for multimedia content analysis. In particular, we focus on the problem of street landmark localization from images. Instead of modeling and matching a street landmark as a whole, our proposed approach extracts the landmark's object fingerprints in a given image and match to a new image or video in order to localize the landmark. We formulate matching the landmark's object fingerprints as a classification problem solved by a cascade of 1NN classifiers. We develop a street landmark localization system that combines salient region detection, segmentation, and object fingerprint extraction techniques for the purpose. To evaluate, we have compiled a novel dataset which consists of 15 U.S. street landmarks' images and videos. Our experiments on this dataset show superior performance to state-of-the-art recognition algorithms [20,33]. The proposed approach can also be well generalized to other objects of interest and content analysis tasks. We demonstrate the feasibility through the application of our approach to refine web image search results and obtained encouraging results.

show abstract

“…Noor et al 12 present a model generation approach for object recognition, using multiple views of objects to build a model database. They start with scale invariant feature transform (SIFT) 13 descriptors for relevant corner point extraction, used to build a region-neighborhood graph that is used for object matching.…”

Section: Introductionmentioning

confidence: 99%

Flying target detection and recognition by feature fusion

Kovács

Utasi

et al. 2012

Opt. Eng

View full text Add to dashboard Cite

We present a near-real-time visual-processing approach for automatic airborne target detection and classification. Detection is based on fast and robust background modeling and shape extraction, while recognition of target classes is based on shape and texture-fused querying on a-priori built real datasets. The presented approach can be used in defense and surveillance scenarios where passive detection capabilities are preferred (or required) over a secured area or protected zone.

show abstract

Model generation for video-based object recognition

Cited by 12 publications

References 6 publications

Lightweight Active Object Retrieval with Weak Classifiers

Lightweight Active Object Retrieval with Weak Classifiers

Object fingerprints for content analysis with applications to street landmark localization

Flying target detection and recognition by feature fusion

Contact Info

Product

Resources

About