Abstract
Effective object detection must be able to handle cluttered visions which convert into the object size, location, orientation, and other movements. We presumed that Computer Vision System Toolbox™ MathWorks offers a variety of techniques for handling challenges in object detection. In this paper, we elaborate on how to detect an object in a cluttered scene, given a reference image of the object. The output of this paper explains an algorithm for detecting a recognized object depending on finding the vision points correspondences between reference and target images. It can detect each and every object in spite of a scale change or in-plane rotation and quite extend to robust with small amounts of out-of-plane rotation. This method of object detection through recognized feature points works best for objects that exhibit non-repeating texture patterns, which give rise to unique feature matches. In connection with this, present algorithm is designed for detecting a specific static object only.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lowe DG (2004) Distinctive image features from scale-invariant key points. Int J Comput Vision 60(2):91–110
Reddy BS, Chatterji BN (1996) An FFT-based technique for translation rotation, and scale-invariant image registration. IEEE Trans Image Process 3(8):1266–1270
Bojiao D, Donghua Z (2007) Fast matching method based on NCC. Transducer Microsyst Technol 26(9):104–106
Ommer B, Malik J (2009) Multi-scale object detection by clustering lines. In: 12th International conference on computer vision
Nagase M, Akizuki S, Hashimoto M (2013) 3-D feature point matching for object recognition based on estimation of local shape distinctiveness. In: International conference on computer analysis of images and patterns, pp. 473–481
Yan Y, Xia H, Huang S, Xiao W (2014) An improved matching algorithm for feature points matching. In: International conference on signal processing, communications and computing
Ben-Musa AS, Singh SK, Agrawal P (2014) Object detection and recognition in cluttered scene using Harris Corner Detection. In: International conference on control, instrumentation, communication and computational technologies
Reddy KR, Krishna KVS, Kumar VR (2014) Detection of objects in cluttered scenes using matching technique. Int J Electron CommunTechnol 5(3):42–44
Sravani C, Harikrishna B, Gayatri K, Anusha K, Pydiraju K (2015) Object capturing in a cluttered scene by using point feature matching. Int J Eng Res Appl 5(3):49–52
Bodke VS, Vaidya OS (2017) Object recognition in a cluttered scene using point feature matching. Int J Res Appl Sci Eng Technol 5(IX):286–290
Patil S, Patil NC (2015) Object localization using putative point matching in cluttered scene. J Emerg Technol Innov Res 2(6):3088–3092
Lee T, Fidler S, Levinshtein A, Sminchisescu C, Dickinson S (2015) A framework for symmetric part detection in cluttered scenes. Symmetry 7:1333–1351
Ratanasanya S, Polvichai J, Sirinaovakul B (2015) Feature point matching with matching distribution. Recent Adv Inf Commun Technol 9–18
Tsai WK, Sheu MH (2016) An efficient foreground object detection method using a color cluster-based background modeling algorithm. In: International symposium on computer, consumer and control
Random photography (2016) Place: Ultadanga, Golaghata, camera model: Nikon D90, resolution: 4288 × 2848 (12.3 effective megapixels) edited with snapseed courtesy by: Partha Mukherjee
Santra S, Mandal S (2018) A new approach towards invariant shape descriptor tools for shape classification through morphological analysis of image. In: 2nd International conference on computational advancement in communication circuit and system
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Santra, S., Mukherjee, P., Sardar, P., Mandal, S., Deyasi, A. (2020). Object Detection in Clustered Scene Using Point Feature Matching for Non-repeating Texture Pattern. In: Basu, T., Goswami, S., Sanyal, N. (eds) Advances in Control, Signal Processing and Energy Systems. Lecture Notes in Electrical Engineering, vol 591. Springer, Singapore. https://doi.org/10.1007/978-981-32-9346-5_7
Download citation
DOI: https://doi.org/10.1007/978-981-32-9346-5_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-32-9345-8
Online ISBN: 978-981-32-9346-5
eBook Packages: EngineeringEngineering (R0)