Self-supervised Feature Detection and Binary Description in Hamming Space for Mobile Platforms

Author(s):  
Shenghao Li ◽  
Guibao Zhang ◽  
Qunfei Zhao
Author(s):  
Hesham Ismail ◽  
Balakumar Balachandran

Simultaneous localization and mapping (SLAM) is a technique used to determine the location of a mobile vehicle in an unknown environment, while constructing a map of the unknown environment at the same time. Mobile platforms, which make use of SLAM algorithms, have industrial applications in autonomous maintenance, such as the inspection of flaws and defects in oil pipelines and storage tanks. An important component of SLAM is feature extraction, which is the process of detecting and extracting significant features such as corners, edges, and walls in an environment. Here, the use of sonars as sensors mounted on a mobile platform is examined, and a comparison of different algorithms currently in use is made and presented. This comparison is performed through a combination of experimental and numerical studies. The triangulation-based fusion algorithm is examined for point feature detection, and the standard Hough Transform and the triangulation Hough fusion (THF) are used for line detection. Comparisons are discussed and presented along with ongoing work.


2013 ◽  
Vol 23 (3) ◽  
pp. 82-87 ◽  
Author(s):  
Eva van Leer

Mobile tools are increasingly available to help individuals monitor their progress toward health behavior goals. Commonly known commercial products for health and fitness self-monitoring include wearable devices such as the Fitbit© and Nike + Pedometer© that work independently or in conjunction with mobile platforms (e.g., smartphones, media players) as well as web-based interfaces. These tools track and graph exercise behavior, provide motivational messages, offer health-related information, and allow users to share their accomplishments via social media. Approximately 2 million software programs or “apps” have been designed for mobile platforms (Pure Oxygen Mobile, 2013), many of which are health-related. The development of mobile health devices and applications is advancing so quickly that the Food and Drug Administration issued a Guidance statement with the purpose of defining mobile medical applications and describing a tailored approach to their regulation.


2007 ◽  
Author(s):  
Jan Theeuwes ◽  
Erik van der Burg ◽  
Artem V. Belopolsky

2018 ◽  
Vol 2018 (6) ◽  
pp. 115-1-115-11
Author(s):  
Devasena Inupakutika ◽  
Chetan Basutkar ◽  
Sahak Kaghyan ◽  
David Akopian ◽  
Patricia Chalela ◽  
...  
Keyword(s):  

2017 ◽  
Vol 2 (1) ◽  
pp. 80-87
Author(s):  
Puyda V. ◽  
◽  
Stoian. A.

Detecting objects in a video stream is a typical problem in modern computer vision systems that are used in multiple areas. Object detection can be done on both static images and on frames of a video stream. Essentially, object detection means finding color and intensity non-uniformities which can be treated as physical objects. Beside that, the operations of finding coordinates, size and other characteristics of these non-uniformities that can be used to solve other computer vision related problems like object identification can be executed. In this paper, we study three algorithms which can be used to detect objects of different nature and are based on different approaches: detection of color non-uniformities, frame difference and feature detection. As the input data, we use a video stream which is obtained from a video camera or from an mp4 video file. Simulations and testing of the algoritms were done on a universal computer based on an open-source hardware, built on the Broadcom BCM2711, quad-core Cortex-A72 (ARM v8) 64-bit SoC processor with frequency 1,5GHz. The software was created in Visual Studio 2019 using OpenCV 4 on Windows 10 and on a universal computer operated under Linux (Raspbian Buster OS) for an open-source hardware. In the paper, the methods under consideration are compared. The results of the paper can be used in research and development of modern computer vision systems used for different purposes. Keywords: object detection, feature points, keypoints, ORB detector, computer vision, motion detection, HSV model color


Author(s):  
Suresha .M ◽  
. Sandeep

Local features are of great importance in computer vision. It performs feature detection and feature matching are two important tasks. In this paper concentrates on the problem of recognition of birds using local features. Investigation summarizes the local features SURF, FAST and HARRIS against blurred and illumination images. FAST and Harris corner algorithm have given less accuracy for blurred images. The SURF algorithm gives best result for blurred image because its identify strongest local features and time complexity is less and experimental demonstration shows that SURF algorithm is robust for blurred images and the FAST algorithms is suitable for images with illumination.


2020 ◽  
Vol 4 (3) ◽  
pp. 591-600
Author(s):  
Mochammad Rizky Royani ◽  
Arief Wibowo

The development of e-commerce in Indonesia in the last five years has significantly increased the growth for logistics service companies. The Indonesian Logistics and Forwarders Association (ALFI) has predicted the growth potential of the logistics business in Indonesia to reach more than 30% by 2020. One of the efforts of logistics business companies to improve services in the logistics services business competition is to implement web service technology on mobile platforms, to easy access to services for customers. This research aims to build a web service with a RESTful approach. The REST architecture has limitations in the form of no authentication mechanism, so users can access and modify data. To improve its services, JSON Web Token (JWT) technology is needed in the authentication process and security of access rights. In terms of data storage and transmission security, a cryptographic algorithm is also needed to encrypt and maintain confidentiality in the database. RC4 algorithm is a cryptographic algorithm that is famous for its speed in the encoding process. RC4 encryption results are processed with the Base64 Algorithm so that encrypted messages can be stored in a database. The combination of the RC4 method with the Base64 method has strengthened aspects of database security. This research resulted in a prototype application that was built with a combination of web service methods, JWT and cryptographic techniques. The test results show that the web service application at the logistics service company that was created can run well with relatively fast access time, which is an average of 176 ms. With this access time, the process of managing data and information becomes more efficient because before making this application the process of handling a transaction takes up to 20 minutes.


2020 ◽  
Author(s):  
Matthew Philip Kaesler ◽  
John C Dunn ◽  
Keith Ransom ◽  
Carolyn Semmler

The debate regarding the best way to test and measure eyewitness memory has dominated the eyewitness literature for more than thirty years. We argue that to resolve this debate requires the development and application of appropriate measurement models. In this study we develop models of simultaneous and sequential lineup presentations and use these to compare the procedures in terms of discriminability and response bias. We tested a key prediction of the diagnostic feature detection hypothesis that discriminability should be greater for simultaneous than sequential lineups. We fit the models to the corpus of studies originally described by Palmer and Brewer (2012, Law and Human Behavior, 36(3), 247-255) and to data from a new experiment. The results of both investigations showed that discriminability did not differ between the two procedures, while responses were more conservative for sequential presentation compared to simultaneous presentation. We conclude that the two procedures do not differ in the efficiency with which they allow eyewitness memory to be expressed. We discuss the implications of this for the diagnostic feature detection hypothesis and other sequential lineup procedures used in current jurisdictions.


2019 ◽  
Vol 31 (6) ◽  
pp. 844-850 ◽  
Author(s):  
Kevin T. Huang ◽  
Michael A. Silva ◽  
Alfred P. See ◽  
Kyle C. Wu ◽  
Troy Gallerani ◽  
...  

OBJECTIVERecent advances in computer vision have revolutionized many aspects of society but have yet to find significant penetrance in neurosurgery. One proposed use for this technology is to aid in the identification of implanted spinal hardware. In revision operations, knowing the manufacturer and model of previously implanted fusion systems upfront can facilitate a faster and safer procedure, but this information is frequently unavailable or incomplete. The authors present one approach for the automated, high-accuracy classification of anterior cervical hardware fusion systems using computer vision.METHODSPatient records were searched for those who underwent anterior-posterior (AP) cervical radiography following anterior cervical discectomy and fusion (ACDF) at the authors’ institution over a 10-year period (2008–2018). These images were then cropped and windowed to include just the cervical plating system. Images were then labeled with the appropriate manufacturer and system according to the operative record. A computer vision classifier was then constructed using the bag-of-visual-words technique and KAZE feature detection. Accuracy and validity were tested using an 80%/20% training/testing pseudorandom split over 100 iterations.RESULTSA total of 321 total images were isolated containing 9 different ACDF systems from 5 different companies. The correct system was identified as the top choice in 91.5% ± 3.8% of the cases and one of the top 2 or 3 choices in 97.1% ± 2.0% and 98.4 ± 13% of the cases, respectively. Performance persisted despite the inclusion of variable sizes of hardware (i.e., 1-level, 2-level, and 3-level plates). Stratification by the size of hardware did not improve performance.CONCLUSIONSA computer vision algorithm was trained to classify at least 9 different types of anterior cervical fusion systems using relatively sparse data sets and was demonstrated to perform with high accuracy. This represents one of many potential clinical applications of machine learning and computer vision in neurosurgical practice.


Sign in / Sign up

Export Citation Format

Share Document