1. Detecting Moving Objects, Ghosts, and Shadows in Video Streams
Rita Cucchiara, Costantino Grana, Massimo Piccardi and Andrea Prati
Adviser : Chih-Hung Lin
Speaker : Kuan-Ju Chen
Date 　　 : 2009/02/19

2. Author
Author
R. Cucchiara, C. Grana, and A. Prati are with the Dipartimento di Ingegneria dell’Informazione, Universita` di Modena e Reggio Emilia, Via Vignolese, 905/b, Modena, Italy.
. M. Piccardi is with Department of Computer Systems, Faculty of IT, University of Technology, Sydney, Broadway NSW 2007, Australia.
Accept
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 25, NO. 10, OCTOBER 2003
revised 23 Sept. 2002; accepted 25 Feb.2003

3. DETECTING MOVING OBJECTS
Contents
INTRODUCTION 1
DETECTING MOVING OBJECTS 2
SHADOW DETECTION 3
RESULTS 4
CONCLUSIONS 5

4. INTRODUCTION
Detection of moving objects in video streams is the first relevant step of information extraction in many computer vision applications
Video surveillance
People tracking
Video surveillance Video監視

5. INTRODUCTION
In this work, the models of the target objects and their motion are unknown
the most widely adopted approach for moving object detection with fixed camera is based on background subtraction
模型的目標物件和他的動作都是未知的，
最廣泛採用的方法的運動目標檢測與固定相機是基於背景減除

6. INTRODUCTION Background Subtraction Two problems
Accurately
Reactivity
If the background model is neither accurate nor reactive
Ghosts
Shadows

7. INTRODUCTION Solution: Statistical combination Combine
Combination frames to compute the background model
Combine
Combine the current frame and previous models with recursive filtering to update the background model

8. INTRODUCTION
In this paper, we propose a novel simple method that exploits all these features, combining them so as to efficiently provide detection of moving objects, ghosts, and shadows.
The main contribution
the integration of knowledge of detected objects, shadows, and ghosts in the segmentation process
enhance object segmentation and background update.
的主要貢獻 整合知識的被測物體，陰影，和鬼的分割進程 加強目標分割和背景更新。

9. DETECTING MOVING OBJECTS
The aim
Detect real moving objects.
Avoiding detection of transient spurious objects
Sakbot (Statistical And Knowledge-Based ObjecT detection)
Statistics and knowledge of the segmented objects to improve both background modeling and moving object detection
1.偵測真實移動物體
避免虛假檢測瞬態物體
2.為了實現這些目標，我們提出一個分類對象的興趣，現場

10. DETECTING MOVING OBJECTS
MVO (Moving visual object)
set of connected points belonging to object characterized by nonnull motion
Ghost
a set of connected points detected as in motion by means of background subtraction, but not corresponding to any real moving object
Shadow
a set of connected background points modified by a shadow cast over them by a moving object
set of connected points belonging to object characterized by nonnull motion
一套連接點屬於object的特點是nonnull運動
一套檢測為連接點的方式在運動的背景減法，而不是任何實際的對應移動物體
一組連接點修改背景的陰影在他們的移動物體

11. DETECTING MOVING OBJECTS
Taxonomy

12. DETECTING MOVING OBJECTS
Frame t
background model
Foreground

13. DETECTING MOVING OBJECTS
Get a statistical information
Follow set of
the statistical background model
knowledge-based background model
Using the median function get a statistical information:
If p belong to MVO , p=background model
If p dosen`t belong to MVO, p= statistical background model

14. DETECTING MOVING OBJECTS
used to update the background model to update background model
If p isn`t belong to known object , p=
If p is belong to known object , p=
update background model

15. SHADOW DETECTION
Mean the process of classification of foreground pixels as “shadow points” based on their appearance

16. SHADOW DETECTION Foreground
Ayalyze Hue-Saturation-Value(HSV) color space
Following three condition to mask shadow
identifying as shadows those points
define a darkening effect of shadows
shadow mask:
average image luminance

17. RESULTS The reactivity of the background model.
反應性的背景模型。第一欄包含了背景模型框架＃ 65 。第二列包含一個縮放的詳細幀 ＃ 100 （上圖）和檢測MVOs （黑色）採用像素只有選擇性（下圖） ：誤報的原因是鬼。第三欄的報告 檢測MVO使用Sakbot （上） ，並利用統計背景更新只在幀＃ 134 （下）

18. RESULTS
simply statistical background
pixel-level selective background
statistical and knowledge-based background models
Segmentation is provided via background subtraction including shadow detection.
(a) false positives and (b) false negatives.

19. CONCLUSIONS
This paper has presented Sakbot, a system for moving object detection in image sequences
This system has the unique characteristic of explicitly addressing various troublesome situations such as cast shadows and ghosts.
Cast shadows are detected and removed from the background update function
Ghosts are also explicitly modeled and detected so as to avoid a further cause of undesired background modification
The method is highly computationally cost-effective since it is not severe in computational time
本文提出了Sakbot ，系統的移動物體 檢測圖像序列中。
該系統具有獨特的 特點明確解決各種棘手的情況下 如蒙上陰影和鬼。
蒙上陰影檢測 並從後台更新功能，
Ghost的定義 以避免多餘的背景更新
計算方法是非常符合成本效益 因為它沒有嚴重的計算時間

20. Thank You !
Add your company slogan

21. DETECTING MOVING OBJECTS
MVOs are validated by applying a set of rules on area, saliency, and motion as follows:
The MVO blob must be large enough
The MVO blob must be a “salient” foreground blob
The MVO blob must have nonnegligible motion

22. DETECTING MOVING OBJECTS
Validation rules

23. Follow set of S
the statistical background model:
knowledge-based background model:
update the background model: