Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Distributed Sensing and Perception via Sparse Representation Allen Y. Yang yang@eecs.berkeley.edu CIS Seminar, Johns Hopkins, 2010 Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Distributed Sensing and Perception: A Comparison Centralized Perception Distributed Perception Up: powerful processors Down: mobile processors Up: unlimited memory Down: limited onboard memory Up: unlimited bandwidth Down: band-limited communications Down: single modality Up: distributed, multi-modality Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Distributed Sensing and Perception: A Comparison Centralized Perception Distributed Perception Up: powerful processors Down: mobile processors Up: unlimited memory Down: limited onboard memory Up: unlimited bandwidth Down: band-limited communications Down: single modality Up: distributed, multi-modality Design an intelligent system over a network that performs better than the sum of its parts? Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Challenges Making real-time decisions on portable mobile devices is difficult. 1 Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Challenges Making real-time decisions on portable mobile devices is difficult. 1 Applications demand extremely high accuracy: 99% Precision, 99% Recall? 2 Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Challenges Making real-time decisions on portable mobile devices is difficult. 1 Applications demand extremely high accuracy: 99% Precision, 99% Recall? 2 Scenarios demand the ability to reconstruct 3-D environments. 3 Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Smart Camera Platform: CITRIC v1 Available library functions CITRIC platform 1 Full support Intel IPP Library and OpenCV . 2 JPEG compression : 10 fps. 3 Edge detector : 3 fps. 4 Background Subtraction : 5 fps. 5 SIFT detector : 10 sec per frame. Academic users: Reference: AY, et al. “CITRIC: A low-bandwidth wireless camera network platform.” (submitted) ACM Trans. Sensor Networks, 2010. Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Body Sensor Platform: DexterNet Body Sensor Layer (BSL) 1 Personal Network Layer (PNL) 2 Global Network Layer (GNL) 3 Reference: AY, et al. “DexterNet: An open platform for heterogeneous body sensor networks and its applications.” Body Sensor Networks, 2009. Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Outline Robust face recognition with low-resolution, distorted, and disguised images 1 Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Outline Robust face recognition with low-resolution, distorted, and disguised images 1 Fast ℓ 1 -Minimization Algorithms 2 x ∗ = arg min � x � 1 subj. to b = A x . x Augmented Lagrange Multiplier Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Outline Robust face recognition with low-resolution, distorted, and disguised images 1 Fast ℓ 1 -Minimization Algorithms 2 x ∗ = arg min � x � 1 subj. to b = A x . x Augmented Lagrange Multiplier Distributed object recognition using a camera network 3 Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Robust Face Recognition Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Classification of Mixture Subspace Model Face-subspace model [Belhumeur et al. ’97, Basri & Jacobs ’03] 1 Assume b belongs to Class i in K classes. b = α i , 1 v i , 1 + α i , 2 v i , 2 + · · · + α i , n 1 v i , n i , = A i α i . Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Classification of Mixture Subspace Model Face-subspace model [Belhumeur et al. ’97, Basri & Jacobs ’03] 1 Assume b belongs to Class i in K classes. b = α i , 1 v i , 1 + α i , 2 v i , 2 + · · · + α i , n 1 v i , n i , = A i α i . Nevertheless, Class i is the unknown label we need to solve: 2 α 1 2 3 α 2 5 = A x . . Sparse representation b = [ A 1 , A 2 , · · · , A K ] . 4 . α K Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Classification of Mixture Subspace Model Face-subspace model [Belhumeur et al. ’97, Basri & Jacobs ’03] 1 Assume b belongs to Class i in K classes. b = α i , 1 v i , 1 + α i , 2 v i , 2 + · · · + α i , n 1 v i , n i , = A i α i . Nevertheless, Class i is the unknown label we need to solve: 2 α 1 2 3 α 2 5 = A x . . Sparse representation b = [ A 1 , A 2 , · · · , A K ] . 4 . α K x ∗ = [ 0 ··· 0 α T 0 ··· 0 ] T ∈ R n . 3 i Sparse representation x ∗ encodes membership! Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Image Corruption Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Image Corruption Sparse representation + sparse error 1 b = A x + e Occlusion compensation: 2 I ´ „ x « ` A b = | = B w e Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Performance on the AR database Reference: AY, et al. Robust face recognition via sparse representation . IEEE PAMI, 2009. Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Face Alignment Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Face Alignment Seek a 2-D transformation b ◦ τ i = A i x + e . (1) Although � x � 1 is no longer penalized, the problem becomes nonlinear. Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Face Alignment Seek a 2-D transformation b ◦ τ i = A i x + e . (1) Although � x � 1 is no longer penalized, the problem becomes nonlinear. Linear approximation: b ◦ τ i + ∇ τ ( b ◦ τ i ) · ∆ τ i ≈ A i x + e . (2) Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Introduction Face Recognition Fast ℓ 1 -Minimization Algorithms Distributed Object Recognition Conclusion Face Alignment Seek a 2-D transformation b ◦ τ i = A i x + e . (1) Although � x � 1 is no longer penalized, the problem becomes nonlinear. Linear approximation: b ◦ τ i + ∇ τ ( b ◦ τ i ) · ∆ τ i ≈ A i x + e . (2) Convert to a linear equation: b ( k ) = [ A i , − J ( k ) ] w + e , (3) i i where w . i ] T . = [ x T , ∆ τ T Distributed Sensing and Perception via Sparse Representation http://www.eecs.berkeley.edu/~yang
Recommend
More recommend
