Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

38
Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi

Transcript of Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Page 1: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Motion Detection in UAV Videos by

Cooperative Optical Flow and Parametric Analysis

Masaharu Kobashi

Page 2: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Objectives

● Show contrast between simple research videos and UAV videos.

● Describe strengths and weaknesses of well-know conventional techniques.

● Propose a new system designed for robustness.

Page 3: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Overview of Presentation

1. Overview of motion analysis

2. UAV videos and their characteristics

3. Strengths and weaknesses of conventional techniques

4. Design of our new system

5. Performance of our system

Page 4: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

What is motion analysis?

● Motion is a relative concept

– Relative to image plane (static camera)

– Relative to objects in the image

● Factors that make it difficult

– Changing extrinsic and intrinsic camera parameters (Pan, tilt, translation, rotation, and zooming)

– Illumination changes

– Overlap of multiple motions with semi-transparency (dust, fog, mist, glasses, etc.)

Page 5: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Classes of Motion Analysis Methods

1. Detecting flow of regularly-shaped regions

– Optical flow, Patch/Block flow

2. Detecting flow of irregularly-shaped regions

– Segmentation-based flow analysis

– Variable-window/block-based flow analysis

3. Detecting difference between two frames in terms of an objective function

– Parametric motion analysis

Page 6: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Popular Videos for Motion Analysis

Page 7: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

What are UAV videos?

Page 8: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Characteristics of UAV videos

● Noisier and of lower quality than standard videos

– Low bandwidth of UAV transmitter

– Quality of camera

● Constant changes of camera parameters (airplane motion, camera's pan, tilt, zooming)

– Often abrupt and quick changes

● Unrestricted natural scenes

– Including dimly lit scenes, deserts, fields

Page 9: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Contrast betweenResearch videos and UAV videos

(See following demo movies.)

Page 10: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Strengths and Weaknesses ofTechniques Related to

Motion Analysis

● Gradient-based Search● Pyramid-Based Coarse-to-Fine Approach● Optical-Flow-Based Motion Detection● Parametric Motion Estimation● Hybrid Approaches

Page 11: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Gradient-Based Search

● Hill-Climbing for global optimization based on local gradient information

● Examples:

– Lucas-Kanade registration algorithm– Light constancy equation

● Strength:

– Fast (avoiding exhaustive search)● Weakness:

– Brittle (1-pixel support; a pixel noise can derail it)

Page 12: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Pyramid-Based Coarse-to-Fine Approach

● Strengths:

– Can summarize information compactly

– Remedy for range-limited gradient-based methods

Page 13: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Weaknesses of Pyramid

● Fixed coverage of child cells (Fixed partitioning)

● Same information to all child cells

● Vital information can be lost in summarizing process

● All parts of image required to use same number of levels

Page 14: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Results from Pyramid's Weaknesses

● The more levels, the more errors.● Small motion areas suffer unnecessary errors

due to the height of the pyramid needed for areas of greater motion.

● Motion of thin/small parts tends to be detected incorrectly.

Page 15: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Optical-Flow-Based Motion Analysis

● Steps:

1. Detection of flow for all pixels in each frame.

2. Accurate segmentation of the flow into moving and stationary objects.

Page 16: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Strengths and Weaknesses of

Optical-flow-Based Motion Analysis

● Strength:

– Dense motion information (for every pixel) available.

● Weaknesses:

– Difficult to obtain accurate vectors for all pixels.– Segmenting flow into multiple moving and static

objects is difficult.

Page 17: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Difficulties in Finding Flow Discontinuity

Page 18: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Parametric Motion Estimation

● Steps:1. Assume a model of transformation (Affine,

Perspective).

2. Compute transformation matrix of the static regions from the point correspondences of static regions.

3. Find point correspondences between two frames f1 and f2.

4. Find difference between frame f1 and an image created by warping frame f2 by the transformation matrix.

Page 19: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Strengths and Weaknesses of Parametric Motion Estimation

● Strengths:

1. Capable of precise matching between frames at all points even at sub-pixel precision.

2. Unlike optical flow analysis, it can find different motion layers equally well in any transformation.

● Weaknesses:

1. Needs reasonably accurate point correspondences.

2. Must know which points belong to static region.

Page 20: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Hybrid Approach

● Use of multiple motion detection techniques in a single system (e.g. optical flow detection + parametric motion estimation)

● Examples:

– Wang and Adelson's motion layers– Our system

Page 21: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Overview of Our System

● Design philosophy:

1. Hybrid system based upon optical flow detector and parametric motion estimator

2. Takes advantage of strengths of both and avoid their weaknesses

3. Priority on robustness rather than efficiency

● System structure

Page 22: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Module 1: Optical Flow Detector

● Block matching with relatively large block (16x16)

● Use of Disk Balance Ratios (DBR)

● Use of Sum of Squared Error (SSD)

Page 23: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Disk Balance Ratios (DBR)

● Objective: – To describe the orientation of a region in

terms of intensity.● Definition:

Page 24: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Limitations of SSD

Page 25: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Use of Sum of Squared Difference (SSD)

● Steps to find the flow vector of block i:1. If the SSD distribution is too flat among candidates, make

no decision. (Near homogeneous region.)

2. If there are two or more candidates which have distinctively better SSD than the rest and flow vectors from block i to these candidates are far apart, make no decision. (Aperture problem.)

3. Otherwise, find the candidate block having the least SSD. The vector from block i to that candidate is the flow vector of block i.

Page 26: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Module 2: Extraction of Reliable Flow

● Reliable flow is defined by the following reliability measure.

Page 27: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Module 3:Finding Connected Reliable Flow Groups

● A variant of the single-link clustering algorithm.

● Connect adjacent reliable blocks if their flow vectors are similar in both angle and magnitude.

Page 28: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Module 4:Finding Ground-Covering Flow Groups

● Steps:

1. If there is a group whose area is more than 40% of the screen, the group is regarded to cover the ground only.

2. If available, use the grouping information of the previous frame in the following way:

• For a group “g”, if more than 70% of the area of g is covered by the ground region in its predecessor frame, then g belongs to the ground. Otherwise, make the decision by the next step.

3. Select the set of groups that minimizes the SSD between the intensities of corresponding pixels between the template frame and the image created by warping the next frame by the inverse of the transformation matrix.

Page 29: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Computation of Transformation Matrix

Page 30: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.
Page 31: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Singular Value Decomposition (SVD)

● Merit:

– Capable of handling even singular matrix

Page 32: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Module 5:Evaluation of Difference Data

● Steps:

1. Compute the mean difference “m” of all pixels in the reliable ground blocks.

2. Exclude the reliable ground blocks from the search region for the moving objects.

3. In the remaining blocks find the pixels whose difference value is greater than m+1.5.

4. Remove isolated small regions from the list of candidate regions.

5. Mark all blocks which contains a candidate region as candidate blocks.

6. Form connected components of candidate blocks. Each connected set of blocks is a moving object.

7. For each connected set of blocks, output its bounding box to indicate the location of the moving object.

Page 33: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Output

Page 34: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Performance Comparison

● Lucas-Kanade plus pyramid v.s. Our system● Michael Black's Algorithm v.s. Our system● Simple research videos v.s. UAV videos

Page 35: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Lucas-Kanade+Pyramid

Page 36: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Lucas-Kanade + Pyramid

Page 37: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Black's Algorithm

Page 38: Motion Detection in UAV Videos by Cooperative Optical Flow and Parametric Analysis Masaharu Kobashi.

Black's Algorithm