Курсы английского
<<  MPEG-2 High Rate Video over 1394 and Implications for 802 MPEG: A Video Compression Standard for Multimedia Applications  >>
Detecting and Tracking Moving Objects for Video Surveillance
Detecting and Tracking Moving Objects for Video Surveillance
Their application sounds familiar
Their application sounds familiar
Approach
Approach
Their Idea
Their Idea
What is “Normal Flow”
What is “Normal Flow”
Computation of Normal Flow
Computation of Normal Flow
Parameter Estimation of the Geometric Transform
Parameter Estimation of the Geometric Transform
Definition of Normal Flow
Definition of Normal Flow
Finding Moving Objects
Finding Moving Objects
Graph Representation of Moving Objects
Graph Representation of Moving Objects
Why is this Difficult
Why is this Difficult
Sample Detection
Sample Detection
Detection Videos
Detection Videos
Example Graph: What’s going on
Example Graph: What’s going on
Attributes of a Node
Attributes of a Node
Keeping Track of Moving Regions
Keeping Track of Moving Regions
Moving objects that don’t appear in some frames can be hypothesized
Moving objects that don’t appear in some frames can be hypothesized
Extraction of Object Trajectories
Extraction of Object Trajectories
Optimal Path
Optimal Path
Optimal Path
Optimal Path
Quantitative Evaluation
Quantitative Evaluation
Evaluation Results on 5 Shots
Evaluation Results on 5 Shots
Tracking Demos
Tracking Demos
Questions/Comments
Questions/Comments

Презентация на тему: «Detecting and Tracking Moving Objects for Video Surveillance». Автор: Linda Shapiro. Файл: «Detecting and Tracking Moving Objects for Video Surveillance.ppt». Размер zip-архива: 1317 КБ.

Detecting and Tracking Moving Objects for Video Surveillance

содержание презентации «Detecting and Tracking Moving Objects for Video Surveillance.ppt»
СлайдТекст
1 Detecting and Tracking Moving Objects for Video Surveillance

Detecting and Tracking Moving Objects for Video Surveillance

Isaac Cohen and Gerard Medioni University of Southern California

2 Their application sounds familiar

Their application sounds familiar

Video surveillance Sensors with pan-tilt and zoom Sensors mounted on moving airborne platforms Requirement for detection and tracking of moving objects and the relationship of their trajectories Requirement for high-level description of the whole video sequence

3 Approach

Approach

First find optical flow and perform motion compensation to stabilize. Find large numbers of moving regions. Use the residual flow field and its normal component to detect errors. Define a attributed graph whose nodes are detected regions and edges are possible matches between two regions detected in two different frames. Use the graph as a dynamic template for tracking moving objects.

4 Their Idea

Their Idea

Detection after stabilization doesn’t work well. So integrate the detection into the stabilization algorithm by locating regions of the image where a residual motion occurs using the normal component of the optical flow field.

5 What is “Normal Flow”

What is “Normal Flow”

The optical flow equation constrains the image velocity in the direction of the local image gradient, but not the tangential velocity. Normal flow corresponds to the image velocity along the image gradient. It is computed from both image gradients and temporal gradients of the stabilized sequence. The amplitude is large near moving regions. The amplitude is near zero near stationary regions.

6 Computation of Normal Flow

Computation of Normal Flow

Let ?ij denote the warping of image to reference frame j.

The stabilized image sequence is defined by Ii(?ij) . Given reference image I0 and target I1, image stabilization consists of registering the two images and computing the geometric transform ? that warps I1 so it aligns with I0.

7 Parameter Estimation of the Geometric Transform

Parameter Estimation of the Geometric Transform

Minimize the least squares equation Detect and remove outliers through an iterative process.

8 Definition of Normal Flow

Definition of Normal Flow

The warping function is integrated into the formula so that the image gradients are computed on the original image grids and not the warped ones. This simplifies the computation and allows for a more accurate estimation of the residual normal flow.

9 Finding Moving Objects

Finding Moving Objects

Given a pair of image frames, find the moving objects by thresholding the normal flow. Does this overcome problems of other approaches?

10 Graph Representation of Moving Objects

Graph Representation of Moving Objects

Nodes are the moving regions. Edges are the relationships between 2 moving regions detected in 2 separate frames. Each new frame generates a set of regions corresponding to the moving objects. We want to know which moving objects in the new frame are the same as those in the old.

11 Why is this Difficult

Why is this Difficult

Little information about the objects is known. Objects tend to be of small size in aerial imagery. Large changes in object size are possible.

12 Sample Detection

Sample Detection

13 Detection Videos

Detection Videos

seq1.avi seq1_det.avi seq6.avi seq6_det.avi

14 Example Graph: What’s going on

Example Graph: What’s going on

15 Attributes of a Node

Attributes of a Node

16 Keeping Track of Moving Regions

Keeping Track of Moving Regions

Among the detected regions, some small ones should be merged into a larger one. They cluster the detected regions in the graph, instead of using single images. Use a median shape template to keep track of the different moving regions.

17 Moving objects that don’t appear in some frames can be hypothesized

Moving objects that don’t appear in some frames can be hypothesized

hypothesized

18 Extraction of Object Trajectories

Extraction of Object Trajectories

The graph representation changes as new frames are acquired and processed. The goal is to find the full trajectory of each moving object. But we don’t know where each one starts or where it ends. So we have to consider each node with no predecessor a possible start and each with no successor a possible end.

19 Optimal Path

Optimal Path

Assign each edge of the graph a cost, which is the similarity between the connected nodes.

cij = Cij / (1 + dij2)

i

j

Cij is the gray-level and shape correlation between i and j. dij is the distance between their centroids.

20 Optimal Path

Optimal Path

This formulation does not lead to the optimal solution. Instead they define the length lj of node j as the maximal length of the path starting at that node. Then the modified cost function Cij=ljcij is used to find the optimal paths from each node without predecessor, using a greedy search method.

21 Quantitative Evaluation

Quantitative Evaluation

TP = true positives of moving objects FP = false positives of moving objects FN = false negatives (not detected)

Metrics: DR = TP / (TP + FN) Detection Ratio FAR = FP / (TP + FP) False Alarm Ratio

22 Evaluation Results on 5 Shots

Evaluation Results on 5 Shots

23 Tracking Demos

Tracking Demos

seq1_mos_track.avi seq6_track.avi

24 Questions/Comments

Questions/Comments

Have they solved our problem? Has anyone done better? No one seems to use the metrics. But a 2005 paper by Nicolescu and Medioni compares results of 4 methods on fake sequences (and beats them, of course) Another recent paper by Xiao and Shah says they compared their results to those of Ke and Kanade, Wang and Adelson, and Ayer and Sawhney, but no numbers are given. Can we beat these people?

«Detecting and Tracking Moving Objects for Video Surveillance»
http://900igr.net/prezentacija/anglijskij-jazyk/detecting-and-tracking-moving-objects-for-video-surveillance-107092.html
cсылка на страницу

Курсы английского

25 презентаций о курсах английского
Урок

Английский язык

29 тем
Слайды
900igr.net > Презентации по английскому языку > Курсы английского > Detecting and Tracking Moving Objects for Video Surveillance