Object and Activity Recognition in a Distributed Camera Network
Recommend Documents
Jul 8, 2013 - other cameras, they come to an agreement about the activity class. ...... Computer Vision, Kyoto, Japan, 27 Septemberâ4 October 2009; pp.
while observing them through multiple cameras. We focus our work on multi camera tracking with non overlapping fields of view (FOV). In particular we propose ...
capturing holes in the coverage, performing tracking of agents, and identifying ...... only differences are that P ts1 is replaced by P ts2, mentions of primary are ...
Supporting Video Adaptation .... processing and transmission burden away from dedicated .... the entire system; receivers query the server to receive camera.
Jan 17, 2018 - Camera-monitoring system for mirrorless car ... 2) Real-time object recognition using Mitsubishi Electric
in distributed problems that require resource balance, low cost distribution plans, ... selected, as a case study, a gas distribution network in which we find all the ...
we are planning to use a SmartCam, i.e. a camera with integrated CPU, in the final implementation of the system. This eliminates the need for a separate ...
adequate in scope and quality as a dissertation for the degree of Doctor of. Philosophy. ... In addition to tracking, we also consider two relevant topics, namely camera node se- ... I am grateful to many people that made this work possible. First ..
adequate in scope and quality as a dissertation for the degree of Doctor of. Philosophy. ... and moving occluders using a wireless camera network. ..... Most previous work on tracking with multiple cameras has focused on tracking all the ...
that combines the similarity scores of neighboring cameras to come up with a probability for each action at the network level. Thorough ...... camera, as shown in Figure 3(d) and explained below. In order to ...... Multi-view gymnastic activity.
Action sequence recognition is then handled using a discriminative Hidden Markov Model (HMM). RADiaL ..... We chose an Asus Xtion Pro Live RGB-D camera.
Horatio Caine. â . , Xin Yao. â and Bernhard Rinner. â. â. Institute of Networked and Embedded Systems, Alpen-Adria Universität Klagenfurt and Lakeside Labs, ...
the network algorithm execution. We have extended Titan with pattern classifiers and enable it to recognize user ac- tivities. In this paper we present how TinyOS ...
propose a generic component-based framework for activity recognition. ... of processing. In this paper we introduce a framework ... classifiers are applied to audio data to recognize the .... thus the tasks of the modules of a source are context.
How to Use This User's Guide . ..... The User's Guide is designed to be read on
the computer display. ... User's Guide show the SNC-VB600 as an example.
Do not lift the camera by only holding the cables. .... This Installation Manual
describes the names and functions of parts and ..... F1.2/AGC 42 dB/50 IRE (IP).
Network Camera. User's Guide. Software Version 1.5. Before operating the unit,
please read this manual thoroughly and retain it for future reference.
The updates will be added to the new version of this manual. ... performance or
reliability of the security or signaling aspects of ... 1.2 Camera Wiring Diagram.
May 15, 2013 ... Installation Manual of Network Camera. 1. Thank you for .... reliability of the
security or signaling aspects of this product. UL MAKES NO ...
rectangular track is placed 9 cm (3 Rx positions) away from the edge of the positioning ... The âarray Xâ configuration is used for positions along the shorter edge, ...
Apr 27, 2018 - First is the detection of moving objects in the foreground; second is the ... commands through its integrated web server [1]. In most of the cases, the. PTZ-IP cameras are either manually operated or programmed under ..... objects ente
May 14, 2007 - Robust extraction of structural, view-invariant features from images, however, has proved to be difficult for computer vision. Therefore ... work, which can learn and recognize objects from natural visual input in a con- .... means tha
Reichardt, Malgorzata Janson, Thomas Zwick, Werner Wiesbeck, Tobias DeiÃler and ..... on a robust transfer of the algorithms from laboratory conditions to a more realistic indoor .... on geometrical optics and the uniform theory of diffraction. ....
Object and Activity Recognition in a Distributed Camera Network
in a Distributed Camera Network. N. Naikal, D. Singaraju and S. S. Sastry.
SWARM Lab Summer Retreat 2012. 5/18/2012. Sastry Research Group. 1 ...
Object and Activity Recognition in a Distributed Camera Network N. Naikal, D. Singaraju and S. S. Sastry SWARM Lab Summer Retreat 2012.
5/18/2012
Sastry Research Group
1
Motivation
•
Interesting objects/landmarks and events are commonly viewed by smart camera networks. – Examples: Security cameras, smart-phones, sports/media coverage, etc.
•
Large volumes of visual data available.
•
Goal: Leveraging multiple views of common objects and events to improve recognition.
• Future setup – network of 50 cameras in Cory 337. 5/18/2012
Sastry Research Group
3
Outline • Distributed object recognition. – Efficient system for recognition of landmarks in wireless camera networks. – Scheme for informative feature selection.
• Human activity recognition – Model for detection of articulated objects in single view. – Propose extension to multiple views. 5/18/2012
Sastry Research Group
4
Landmark Recognition in Camera Network Given training images of landmarks in pre-defined categories; Assign category label to query images.
• System constraints – Cameras have limited processing power. – Band-limited communication channel. – No inter-camera calibration assumed. 5/18/2012
Sastry Research Group
5
Bag-of-Words (BoW) Framework
Keypoint
Keypoint
Extraction
Extraction
Codeword Quantization
Visual Words Representation 5/18/2012
Sastry Research Group
6
System Pipeline
•
Visual word histograms are non-negative and sparse.
•
Compress using random projection (Coefficients of 𝐴 ∈
•
ℝ𝑑×𝐷
𝒃𝑘 = 𝐴𝒙𝑘 drawn from zero-mean Gaussian distribution).
Decompress using 𝑙1 -minimization 𝒙𝒌 = arg min 𝒙
5/18/2012
1
subject to 𝒃𝒌 = 𝐴𝒙
Sastry Research Group
7
Large Baseline Results
5/18/2012
Sastry Research Group
8
Irrelevant Feature Suppression
Keypoints returned by interest point detector
• Non-useful features generally generated.
• Method needed to eliminate irrelevant features during training. Proposed Sparse Principal Components Analysis to identify informative features 5/18/2012
Informative features correspond to non-zero support of sparse PC
Original Features 5/18/2012
Informative Features Sastry Research Group
10
Performance on BMW Database
• Union of informative features from all categories forms support set. • Total of 400 words in support set. • Visual dictionary constructed with 1000 words.
5/18/2012
Sastry Research Group
11
Models of objects with deformable parts Candidate hypothesis
(𝑦1 , 𝑦2 , … , 𝑦10 )
𝑦𝑝 : location of the 𝑝𝑡ℎ part.
Felzenszwalb et al. PAMI ‘09, Zhu et al. CVPR ‘10, Yang et al. CVPR ’11. 5/18/2012
Sastry Research Group
12
Towards Unifying Detection and Segmentation • Can we improve the results of the discriminative object detectors by unifying detection and segmentation?
Park and Ramanan. ICCV’11
• How do we define a cost function for unified detection and segmentation? 5/18/2012
Sastry Research Group
13
An Energy Function for Unified Detection and Segmentation
• 𝑑𝑝 𝑦𝑝 ∈ *0, 1+: variable for detection/occlusion of the 𝑝𝑡ℎ part at location 𝑦𝑝 . • 𝑥𝑖 ∈ *0, 1+: segmentation of the 𝑖𝑡ℎ pixel.
+
5/18/2012
Sastry Research Group
14
An Energy Function for Unified Detection and Segmentation
• 𝑑𝑝 𝑦𝑝 ∈ *0, 1+: variable for detection/occlusion of the 𝑝𝑡ℎ part at location 𝑦𝑝 . • 𝑥𝑖 ∈ *0, 1+: segmentation of the 𝑖𝑡ℎ pixel. • 𝒮𝑝 : shape prior for the 𝑝𝑡ℎ part (learned from training data).
𝒮 ℎ𝑒𝑎𝑑
5/18/2012
Sastry Research Group
15
Results from initial tests: input to our algorithm
Given hypothesis for parts’ locations
Hypothesis for location of parts (obtained using existing detectors) 5/18/2012
Probability of each pixel being assigned to the foreground (shape priors)
Sastry Research Group
16
Results from initial tests: output from our algorithm
Given hypothesis for parts’ locations
Locations of the “detected” parts (yellow) and the “rejected” parts (red) 5/18/2012
Sastry Research Group
Segmentation 17
Results from initial tests: input to our algorithm
Hypothesis for location of parts (obtained using existing detectors) 5/18/2012
Probability of each pixel being assigned to the foreground (shape priors)
Sastry Research Group
18
Results from initial tests: output from our algorithm
Locations of the “detected” parts (yellow) and the “rejected” parts (red) 5/18/2012
Sastry Research Group
Segmentation 19
Conclusion • Presented a distributed object/landmark recognition framework for wireless smart cameras. • Demonstrated effectiveness of using Sparse PCA for informative feature selection. • Presented scheme to unify segmentation and detection of articulated models in single images.
Future Work • Using anthropometry constraints to improve human detection in multiple views. • Tracking articulated models in video stream. • Recognizing human activity from reconstructed models.