BRIGHT: A scalable and compact binary descriptor for low-latency and high accuracy object identification

Iwamoto, Kota; Mase, Ryota; Nomura, Toshiyuki

doi:10.1109/icip.2013.6738600

Cited by 8 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Satapathy et al [13] proposed a method to detect products on the shelves by using exhaustive template matching for raising alerts to replenish products. Bao et al [14] proposed a method to accurately identify and locate a large number of objects in an image by using a scalable and compact binary local descriptor, named the BRIGHT (Binary ResIzable Gradient HisTogram) descriptor [15]. Zhang et al [16] proposed a dual-layer density estimation-based architecture to detect multiple object instances from an image for robot inventory management.…”

Section: Related Workmentioning

confidence: 99%

Robust Shelf Monitoring Using Supervised Learning for Improving On-Shelf Availability in Retail Stores

Higa

Iwamoto

2019

Sensors

Self Cite

View full text Add to dashboard Cite

This paper proposes a method to robustly monitor shelves in retail stores using supervised learning for improving on-shelf availability. To ensure high on-shelf availability, which is a key factor for improving profits in retail stores, we focus on understanding changes in products regarding increases/decreases in product amounts on the shelves. Our method first detects changed regions of products in an image by using background subtraction followed by moving object removal. It then classifies the detected change regions into several classes representing the actual changes on the shelves, such as “product taken (decrease)” and “product replenished/returned (increase)”, by supervised learning using convolutional neural networks. It finally updates the shelf condition representing the presence/absence of products using classification results and computes the product amount visible in the image as on-shelf availability using the updated shelf condition. Three experiments were conducted using two videos captured from a surveillance camera on the ceiling in a real store. Results of the first and second experiments show the effectiveness of the product change classification in our method. Results of the third experiment show that our method achieves a success rate of 89.6% for on-shelf availability when an error margin is within one product. With high accuracy, store clerks can maintain high on-shelf availability, enabling retail stores to increase profits.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust Shelf Monitoring Using Supervised Learning for Improving On-Shelf Availability in Retail Stores

Higa

Iwamoto

2019

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Improved sampling patterns were shown to boost performance while still using gradients (Alahi et al, 2012;Leutenegger et al, 2011). Descriptors such as BRIGHT (Iwamoto et al, 2013) introduced a variable bit-string length for mobile applications. An alternative, but very popular way to obtain binary descriptors, is by quantizing more complex descriptors (Strecha et al, 2012;Gong et al, 2013a,b).…”

Section: Related Workmentioning

confidence: 99%

BINK: Biological binary keypoint descriptor

et al. 2017

View full text Add to dashboard Cite

Learning robust keypoint descriptors has become an active research area in the past decade. Matching local features is not only important for computational applications, but may also play an important role in early biological vision for disparity and motion processing. Although there were already some floating-point descriptors like SIFT and SURF that can yield high matching rates, the need for better and faster descriptors for real-time applications and embedded devices with low computational power led to the development of binary descriptors, which are usually much faster to compute and to match. Most of these descriptors are based on purely computational methods. The few descriptors that take some inspiration from biological systems are still lagging behind in terms of performance. In this paper, we propose a new biologically inspired binary keypoint descriptor: BINK. Built on responses of cortical V1 cells, it significantly outperforms the other biologically inspired descriptors. The new descriptor can be easily integrated with a V1-based keypoint detector that we previously developed for real-time applications.

show abstract

“…For our investigation, we select three local binary descriptors: two intensity-based (BRISK [4] and FREAK [3]) and one gradient-based (BRIGHT [14]). Our choice is motivated by their high level of performance in retrieval us- ing descriptor-by-descriptor matching with bi-directional ratio test, but without geometric verification.…”

Section: Global Representations From Local Binary Featuresmentioning

confidence: 99%

On aggregation of local binary descriptors

Husain

Bober

2016

2016 IEEE International Conference on Multimedia &Amp; Expo Workshops (ICMEW)

View full text Add to dashboard Cite

This paper addresses the problem of aggregating local binary descriptors for large scale image retrieval in mobile scenarios. Binary descriptors are becoming increasingly popular, especially in mobile applications, as they deliver high matching speed, have a small memory footprint and are fast to extract. However, little research has been done on how to efficiently aggregate binary descriptors. Direct application of methods developed for conventional descriptors, such as SIFT, results in unsatisfactory performance. In this paper we introduce and evaluate several algorithms to compress high-dimensional binary local descriptors, for efficient retrieval in large databases. In addition, we propose a robust global image representation; Binary Robust Visual Descriptor (B-RVD), with rank-based multi-assignment of local descriptors and direction-based aggregation, achieved by the use of L1-norm on residual vectors. The performance of the B-RVD is further improved by balancing the variances of residual vector directions in order to maximize the discriminatory power of the aggregated vectors. Standard datasets and measures have been used for evaluation showing significant improvement of around 4% mean Average Precision as compared to the state-of-the-art.

show abstract

BRIGHT: A scalable and compact binary descriptor for low-latency and high accuracy object identification

Cited by 8 publications

References 6 publications

Robust Shelf Monitoring Using Supervised Learning for Improving On-Shelf Availability in Retail Stores

Robust Shelf Monitoring Using Supervised Learning for Improving On-Shelf Availability in Retail Stores

BINK: Biological binary keypoint descriptor

On aggregation of local binary descriptors

Contact Info

Product

Resources

About