Embedded Computer Vision

Front Cover
Branislav Kisačanin, Shuvra S. Bhattacharyya, Sek Chai
Springer Science & Business Media, Sep 26, 2008 - Computers - 284 pages
0 Reviews
As a graduate student at Ohio State in the mid-1970s, I inherited a unique c- puter vision laboratory from the doctoral research of previous students. They had designed and built an early frame-grabber to deliver digitized color video from a (very large) electronic video camera on a tripod to a mini-computer (sic) with a (huge!) disk drive—about the size of four washing machines. They had also - signed a binary image array processor and programming language, complete with a user’s guide, to facilitate designing software for this one-of-a-kindprocessor. The overall system enabled programmable real-time image processing at video rate for many operations. I had the whole lab to myself. I designed software that detected an object in the eldofview,trackeditsmovementsinrealtime,anddisplayedarunningdescription of the events in English. For example: “An object has appeared in the upper right corner...Itismovingdownandtotheleft...Nowtheobjectisgettingcloser...The object moved out of sight to the left”—about like that. The algorithms were simple, relying on a suf cient image intensity difference to separate the object from the background (a plain wall). From computer vision papers I had read, I knew that vision in general imaging conditions is much more sophisticated. But it worked, it was great fun, and I was hooked.
 

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

762 Performance of Single Features
151
763 Performance of Combined Features
155
77 FPGA Implementation on Videoware
156
78 Conclusions
160
References
161
Embedded RealTime Surveillance Using Multimodal Mean Background Modeling
163
82 Related Work
164
83 Multimodal Mean Background Technique
166

152 FieldProgrammable Gate Arrays
15
153 Graphics Processing Units
17
154 Smart Camera Chips and Boards
18
155 Memory and Mass Storage
19
156 System on Chip
20
157 CPU and Auxiliary Boards
21
16 Processing Board Organization
22
17 Conclusions
24
References
25
Design Methodology for Embedded Computer Vision Systems
27
22 Algorithms
30
23 Architectures
31
24 Interfaces
33
25 Design Methodology
35
252 Partitioning and Mapping
37
253 Scheduling
38
254 Design Space Exploration
40
255 Code Generation and Verification
41
26 Conclusions
43
We Can Watch It for You Wholesale
49
32 Video Analytics Goes DownMarket
51
321 What Does Analytics Need to Do?
52
UseCases for Video Analytics
54
33 How Does Video Analytics Work?
56
331 An Embedded Analytics Architecture
57
332 Video Analytics Algorithmic Components
59
by the Numbers
66
341 Putting It All Together
67
342 Analysis of Embedded Video Analytics System
68
35 Future Directions for Embedded Video Analytics
70
351 Surveillance and Monitoring Applications
71
352 Moving Camera Applications
72
36 Conclusion
74
References
75
Using Robust Local Features on DSPBased Embedded Systems
79
42 Related Work
81
43 Algorithm Selection
82
432 DoG Keypoints
83
433 MSER
84
434 PCASIFT
85
436 Epipolar Geometry
86
44 Experiments
87
442 Object Recognition
90
45 Conclusion
97
References
99
Benchmarks of LowLevel Vision Algorithms for DSP FPGA and Mobile PC Processors
101
52 Related Work
103
54 Implementation
104
542 FPGA Implementation
106
543 DSP Implementation
111
544 Mobile PC Implementation
115
55 Results
117
56 Conclusions
118
References
119
SADBased Stereo Matching Using FPGAs
121
62 Related Work
122
63 Stereo Vision Algorithm
123
64 Hardware Implementation
125
642 Optimizing the SAD
126
643 TreeBased WTA
128
65 Experimental Evaluation
129
652 Results
130
653 Comparison
134
66 Conclusions
137
Motion History Histograms for Human Action Recognition
139
72 Related Work
141
73 SVMBased Human Action Recognition System
142
74 Motion Features
143
742 Limitations of the MHI
144
743 Definition ofMHH
145
744 Binary Version of MHH
147
75 Dimension Reduction and Feature Combination
148
754 Combining Features
149
76 System Evaluation
150
84 Experiment
168
eBox2300 Thin Client
169
85 Results and Evaluation
170
851 eBox Performance Results and Storage Requirements
172
86 Conclusion
174
References
175
Implementation Considerations for Automotive Vision Systems on a FixedPoint DSP
177
911 FixedPoint vs FloatingPoint Arithmetic Design Process
179
912 Code Conversion
180
92 FixedPoint Arithmetic
182
932 BitTrue FixedPoint Simulation
185
94 Implementation Considerations for SingleCamera Steering Assistance Systems on a FixedPoint DSP
186
95 Results
190
96 Conclusions
193
References
194
Towards Open VL Improving RealTime Performance of Computer Vision Applications
195
102 Related Work
197
1022 Pipes and Filters and DataFlow Approaches
198
1023 OpenGL
199
1024 Hardware Architecture for Parallel Processing
200
103 A Novel Software Architecture for OpenVL
201
1032 Stacks
205
1033 EventDriven Mechanism
206
1035 Synchronization and Communication
207
1036 Iteration
209
1037 Isolating Layers to Mask Heterogeneity
210
104 Example Application Designs
211
1043 Human Tracking and Attribute Calculation
214
106 Acknowledgements
215
Mobile Challenges for Embedded Computer Vision
219
112 In Search of the Killer Applications
221
1122 Video Codec
222
1124 Example Applications
223
113 Technology Constraints
224
1132 Computing Platform
226
1133 Memory
227
1135 Cost and Performance
228
1137 Illumination and Optics
229
114 Intangible Obstacles
230
1142 Measurability and Standardization
231
1143 Business Models
232
References
233
Challenges in Video Analytics
237
122 Current Technology and Applications
238
1221 Video Surveillance
240
1222 Retail
241
1223 Transportation
243
123 Building Blocks
244
1231 Segmentation
245
1232 Classification and Recognition
246
1233 Tracking
247
1234 Behavior and Activity Recognition
248
125 Future Applications and Challenges
250
1252 MultiCamera Tracking
251
1253 Smart Cameras
252
1255 Search and Retrieval
253
1256 Vision for an AnalyticsPowered Future
254
References
255
Challenges of Embedded Computer Vision in Automotive Safety Systems
257
132 Literature Review
258
133 Vehicle Cueing
259
Edge Detection and Processing
260
SizedEdge detection
261
Symmetry Detection
262
Classification
265
Vehicle Border Refinement
266
134 Feature Extraction
268
1342 EdgeBased Density and Symmetry Features
270
1344 Edge Orientation Histogram
271
135 Feature Selection and Classification
274
136 Experiments
276
137 Conclusion
278
Index
280
Copyright

Other editions - View all

Common terms and phrases