People Detection in Color and Infrared Video Using HOG and Linear SVM

Author(s):  
Pablo Tribaldos ◽  
Juan Serrano-Cuerda ◽  
María T. López ◽  
Antonio Fernández-Caballero ◽  
Roberto J. López-Sastre
2004 ◽  
Vol 61 (7-12) ◽  
pp. 875-893 ◽  
Author(s):  
I. A. Vyazmitinov ◽  
Ye. I. Myroshnychenko ◽  
O. V. Sytnik
Keyword(s):  

Crop Science ◽  
2003 ◽  
Vol 43 (1) ◽  
pp. 415 ◽  
Author(s):  
J. C. Stier ◽  
D. L. Filiault ◽  
Michael Wisniewski ◽  
J. P. Palta
Keyword(s):  

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 2958
Author(s):  
Antonio Carlos Cob-Parro ◽  
Cristina Losada-Gutiérrez ◽  
Marta Marrón-Romera ◽  
Alfredo Gardel-Vicente ◽  
Ignacio Bravo-Muñoz

New processing methods based on artificial intelligence (AI) and deep learning are replacing traditional computer vision algorithms. The more advanced systems can process huge amounts of data in large computing facilities. In contrast, this paper presents a smart video surveillance system executing AI algorithms in low power consumption embedded devices. The computer vision algorithm, typical for surveillance applications, aims to detect, count and track people’s movements in the area. This application requires a distributed smart camera system. The proposed AI application allows detecting people in the surveillance area using a MobileNet-SSD architecture. In addition, using a robust Kalman filter bank, the algorithm can keep track of people in the video also providing people counting information. The detection results are excellent considering the constraints imposed on the process. The selected architecture for the edge node is based on a UpSquared2 device that includes a vision processor unit (VPU) capable of accelerating the AI CNN inference. The results section provides information about the image processing time when multiple video cameras are connected to the same edge node, people detection precision and recall curves, and the energy consumption of the system. The discussion of results shows the usefulness of deploying this smart camera node throughout a distributed surveillance system.


Plants ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 1031
Author(s):  
Clara Bertel ◽  
Jürgen Hacker ◽  
Gilbert Neuner

In the temperate zone of Europe, plants flowering in early spring or at high elevation risk that their reproductive organs are harmed by episodic frosts. Focusing on flowers of two mountain and three early-flowering colline to montane distributed species, vulnerability to ice formation and ice management strategies using infrared video thermography were investigated. Three species had ice susceptible flowers and structural ice barriers, between the vegetative and reproductive organs, that prevent ice entrance from the frozen stems. Structural ice barriers as found in Anemona nemorosa and Muscari sp. have not yet been described for herbaceous species that of Jasminum nudiflorum corroborates findings for woody species. Flowers of Galanthus nivalis and Scilla forbesii were ice tolerant. For all herbs, it became clear that the soil acts as a thermal insulator for frost susceptible below ground organs and as a thermal barrier against the spread of ice between individual flowers and leaves. Both ice barrier types presumably promote that the reproductive organs can remain supercooled, and can at least for a certain time-period escape from effects of ice formation. Both effects of ice barriers appear significant in the habitat of the tested species, where episodic freezing events potentially curtail the reproductive success.


2014 ◽  
Vol 75 (17) ◽  
pp. 10769-10786 ◽  
Author(s):  
Carsten Stahlschmidt ◽  
Alexandros Gavriilidis ◽  
Jörg Velten ◽  
Anton Kummert

Sign in / Sign up

Export Citation Format

Share Document