A Confidence Ranked Co-Occurrence Approach for Accurate Object Recognition in Highly Complex Scenes

Date

2013-01-01

Author

Angın, Pelin

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

248
views

0
downloads

Real-time and accurate classification of objects in highly complex scenes is an important problem for the Computer Vision community due to its many application areas. While boosting methods with the sliding window approach provide fast processing and accurate results for particular object categories, they cannot achieve the desired performance for more involved categories of objects. Recent research in Computer Vision has shown that exploiting object context through relational dependencies between object categories leads to improved accuracy in object recognition. While efforts in collective classification in images have resulted in complex algorithms suitable for offline processing, the real-time nature of the problem requires the use of simpler algorithms. In this paper, we propose a simple iterative algorithm for collective classification of all objects in an image, exploiting the global co-occurrence frequencies of object categories. The proposed algorithm uses multiple detectors trained using Gentle Boosting, where the category of the most confident estimate is propagated through the co-occurrence relations to determine the categories of the remaining unclassified objects. Experiments on a real-world dataset demonstrate the superiority of our approach over using Gentle Boosting alone as well as classic collective classification approaches modeling the full joint distribution for each object in the scene.

Subject Keywords

Real-Time, Confidence, Co-occurrence, Object recognition, Computer vision

URI

https://hdl.handle.net/11511/38624

Journal

JOURNAL OF INTERNET TECHNOLOGY

DOI

https://doi.org/10.6138/jit.2013.14.1.02

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Efficient detection and tracking of salient regions for visual processing on mobile platforms Serhat, Gülhan; Saranlı, Afşar; Department of Electrical and Electronics Engineering (2009) Visual Attention is an interesting concept that constantly widens its application areas in the field of image processing and computer vision. The main idea of visual attention is to find the locations on the image that are visually attractive. In this thesis, the visually attractive regions are extracted and tracked in video sequences coming from the vision systems of mobile platforms. First, the salient regions are extracted in each frame and a feature vector is constructed for each one. Then Scale Invaria...
A new approach for better load balancing of visibility detection and target acquisition calculations Filiz, Anıl Yiğit; Can, Tolga; Department of Computer Engineering (2010) Calculating visual perception of entities in simulations requires complex intersection tests between the line of sight and the virtual world. In this study, we focus on outdoor environments which consist of a terrain and various objects located on terrain. Using hardware capabilities of graphics cards, such as occlusion queries, provides a fast method for implementing these tests. In this thesis, we introduce an approach for better load balancing of visibility detection and target acquisition calculations b...
Visual object detection and tracking using local convolutional context features and recurrent neural networks Kaya, Emre Can; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2018) Visual object detection and tracking are two major problems in computer vision which have important real-life application areas. During the last decade, Convolutional Neural Networks (CNNs) have received significant attention and outperformed methods that rely on handcrafted representations in both detection and tracking. On the other hand, Recurrent Neural Networks (RNNs) are commonly preferred for modeling sequential data such as video sequences. A novel convolutional context feature extension is introduc...
A Fast shape detection approach by directional integrations Okman, Osman Erman; Akar, Gözde; Department of Electrical and Electronics Engineering (2013) Detection and identification of objects from aerial images are important problems for various types of application areas. For many of the man-made structures shape is a fundamental feature by which these objects are separated from the background and other structures. In this thesis, a novel geometric shape detection algorithm based on the spatial properties of structures is proposed. Since the objects are transformed into 1-D vectors by evaluating directional integrals and detections occur by the analysis o...
An FPGA based high performance optical flow hardware design for computer vision applications Gultekin, Gokhan Koray; Saranlı, Afşar (2013-05-01) Optical Flow (OF) information is used in higher level vision tasks in a variety of computer vision applications. However, its use in resource constrained applications such as small-scale mobile robotic platforms is limited because of the high computational complexity involved. The inability to compute the OF vector field in real-time is the main drawback which prevents these applications to efficiently utilize some successful techniques from the computer vision literature. In this work, we present the desig...

Citation Formats

P. Angın, “A Confidence Ranked Co-Occurrence Approach for Accurate Object Recognition in Highly Complex Scenes,” JOURNAL OF INTERNET TECHNOLOGY, pp. 13–19, 2013, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/38624.