Integrating Visual Context and Object Detection within a Probabilistic Framework

2009 ◽  
pp. 54-68 ◽  
Author(s):  
Roland Perko ◽  
Christian Wojek ◽  
Bernt Schiele ◽  
Aleš Leonardis
Keyword(s):  
Object Detection ◽  
Visual Context ◽  
Probabilistic Framework

A framework for visual-context-aware object detection in still images

2010 ◽  
Vol 114 (6) ◽  
pp. 700-711 ◽  
Author(s):  
Roland Perko ◽  
Aleš Leonardis
Keyword(s):  
Object Detection ◽  
Visual Context ◽  
Context Aware ◽  
Still Images

A Frustum-based probabilistic framework for 3D object detection by fusion of LiDAR and camera data

2020 ◽  
Vol 159 ◽  
pp. 90-100 ◽  
Author(s):  
Zheng Gong ◽  
Haojia Lin ◽  
Dedong Zhang ◽  
Zhipeng Luo ◽  
John Zelek ◽  
...  
Keyword(s):  
Object Detection ◽  
Probabilistic Framework ◽  
3D Object ◽  
3D Object Detection

Visual context differentially mediates left- and right-hand reaching movements

2009 ◽  
Author(s):  
Jos J. Adam ◽  
Susan Hoonhorst ◽  
Rick Muskens ◽  
Jay Pratt ◽  
Martin H. Fischer
Keyword(s):  
Reaching Movements ◽  
Visual Context ◽  
Right Hand ◽  
Left And Right

Automatic accounting of Baikal diatomic algae: approaches and prospects

2019 ◽  
pp. 295-299
Author(s):  
Кonstantin А. Elshin ◽  
Еlena I. Molchanova ◽  
Мarina V. Usoltseva ◽  
Yelena V. Likhoshway
Keyword(s):  
Object Detection ◽  
Loss Function ◽  
Classification Accuracy ◽  
Diatom Species ◽  
Bounding Box ◽  
Synedra Acus ◽  
And Training

Using the TensorFlow Object Detection API, an approach to identifying and registering Baikal diatom species Synedra acus subsp. radians has been tested. As a result, a set of images was formed and training was conducted. It is shown that аfter 15000 training iterations, the total value of the loss function was obtained equal to 0,04. At the same time, the classification accuracy is equal to 95%, and the accuracy of construction of the bounding box is also equal to 95%.

Object Detection in Cluttered Range Images Using Edgel Geometry

2010 ◽  
Vol 130 (9) ◽  
pp. 1572-1580
Author(s):  
Dipankar Das ◽  
Yoshinori Kobayashi ◽  
Yoshinori Kuno
Keyword(s):  
Object Detection ◽  
Range Images

Narrated Photography

2015 ◽  
Vol 9 (1) ◽  
pp. 30-52
Author(s):  
Sarah Dunlop ◽  
Peter Ward
Keyword(s):  
Qualitative Research ◽  
Material Culture ◽  
Family Relationships ◽  
Research Method ◽  
Religious Practice ◽  
Ethnographic Research ◽  
Lived Religion ◽  
Visual Context ◽  
Textual Material ◽  
Shed Light

This article describes how a recently refined visual ethnographic research method, “narrated photography,” contributes to the study of religion. We argue that this qualitative research method is particularly useful for studies of lived religion and demonstrate this through examples drawn from a study the sacred among young Polish migrants to England. Narrated photography, which entails asking people to photograph what is personally significant to them and then to narrate the image, generates visual and textual material that mediates the subjective. Through using this method we discovered that family was considered to be sacred, both in terms of links to religious practice and a desire for a secure home which family relationships provide. Additionally, narrated photography has the potential to expand our conceptions of lived religion through the inclusion of visual material culture and the visual context of the research participants. In this case the data revealed that the Polish young people view structures within their landscape through a particularly Polish Catholic lens. These findings shed light on the religious tensions that migrants encounter in everyday life.

Sign in / Sign up

Export Citation Format

Share Document