CollaborativeObservationofNaturalEnvironments(CONE)DezhenSongTexasA&MUniversityApr.10th,2010,WorkshoponIntelligentSystems:AFestschriftforRichardVolz,TAMU,CollegeStation,TXThanksto:NiQin,YiliangXu,ChangYoungKim,JiZhangTAMUKenGoldberg,UCBerkeleyRonRohrbach,CornellLabofOrnithologyJohnFitzpatrick,CornellLabofOrnithologyDavidLuneau,UArkansasJohnRappole,SmithsonianSelmaGlasscock,WelderWildlifeFoundationNationalScienceFoundationTheNatureConservancyArkansasGameandFishCommissionU.S.FishandWildlifeServiceArkansasElectricCooperativeCacheRiverNationalWildlifeRefugeoutline• networkedtelerobotsandprojectcone• automatedobservation:ivorybilledwoodpecker• engagingcitizenscientists:birdrangechangeinsouthtexasnikolatesla(1898)teleoperation:relatedwork• Tesla,1898• Goertz,ʻ54• Mosher,ʻ64• Tomovic,ʻ69• Salisbury,Bejczy,ʻ85• Ballard,ʼ86• Volz,ʼ87-• Sheridan,ʻ92• Sato,ʼ94• Goldberg,ʼ94-• PresenceJournalʻ92-• O.Khatib,etal.ʼ96collaborativecontrolnetworkedtelerobotsnetworkedroboticcamera12FrameSelectionProblem:Givennrequests,findoptimalframeProcessingZoomTypeComplexityCentralizedDiscreteExactO(n2)CentralizedDiscreteApproxO(nklog(nk)),k=(log(1/ε)/ε)2CentralizedContin.ExactO(n3)CentralizedContin.ApproxO((n+1/ε3)log2n) DistributedDiscreteExactServer:O(n),Client:O(n)DistributedContin.ApproxServer:O(n),ClientO(1/ε3)p-Frame DiscreteApproxO(n/ε3+p2/ε6)frameselectionalgorithmsbiologicalobservationisarduous,expensive,dangerous,lonelyMotionSensorsPeriodicChecksSensorNetworkStudentsBiologistsCollaborativeframeselection:coneoutline• networkedtelerobotsandprojectcone• automatedobservation:ivorybilledwoodpecker• engagingcitizenscientists:birdrangechangeinsouthtexasDetecting Rare Birds • Low occurrence (e.g., <10 times per year) • Short duration (e.g., < 1 sec. in FOV) • Huge video data for human identification. • Setup and maintenance in remote environments.Design Goals • Accuracy – low false negative • Data reduction – filtering the targeted bird • Easy to setup and maintain – monocular vision system25• Crittercam • DeerCam • Africa web cams at the Te m b e Elephant part • Tiger web cams • James Reserve Wildlife Observatory • Crane Cam • Swan Cam NaturalcamerasRelated Work • Motion detection and tracking – Elgammal, Grimson, Isard … • Periodic motion detection – Culter, Ran, Briassouli … • 3D inference using monocular vision – Ribnick, Hoiem, Saxena …Related Work • Kalman Filter – SLAM, tracking, recognition … – Convergence • ample observation data • manageable noise • less than 11 data points • significant image noiseBird detection problem • Input – targeted bird body length lb and speed range V=[vmin,vmax]. – a sequence of n images containing a moving object • Output – to determine if the object is a bird of targeted speciesAssumptions • Static monocular camera – High resolution – Narrow FOV • Single bird in FOV – Motion segmentation • Constant bird velocity – High flying speed – Narrow camera FOVConjecture 1: Invariant body lengthConjecture 1: Invariant body length [ut,vt]T [uh,vh]T l z=[uh,vh,ut,vt]T (observation)Bird Body Axis Filtering • Conjecture 2: Body axis orientation close to tangent line of trajectory Bird body axis Flying trajectory θ θ Difference between θ and θ on 61bird sequences: BModeling A Flying Bird camera center Image plane [x,y,z]T [ut,vt]T [uh,vh]T x!z!y!lb Ptail Dynamics: Pin-hole model: Tail: lExtended Kalman Filter camera center Image plane x(k+1) z(k) z(k+1) x!z!y!lb x(k) lDetermine Species for Noise-free Cases camera center Image plane Targeted!range!False TrueEKF Convergence MetricsEstimation with Observation Noises camera center Image planeProbable Observation Data Set (PODS) camera center Image plane PODS: Targeted!range!PODS-EKF PODS: Targeted!range!Dezhen Song and Yiliang Yu, A Low False Negative Filter for Detecting Rare Bird Species from Short Video Segments using a Probable Observation Data Set-based EKF Method, IEEE Transactions on Image Processing (Accepted, in press)PODS-EKF Approximate Computation Targeted!range!Dezhen Song and Yiliang Yu, A Low False Negative Filter for Detecting Rare Bird Species from Short Video Segments using a Probable Observation Data Set-based EKF Method, IEEE Transactions on Image Processing (Accepted, in press) Subject to:PODS-EKF Approximate Computation Dezhen Song and Yiliang Yu, A Low False Negative Filter for Detecting Rare Bird Species from Short Video Segments using a Probable Observation Data Set-based EKF Method, IEEE Transactions on Image Processing (Accepted, in press)AlgorithmExperiments: • Testing phase: May 2006 to Oct. 2006 in Texas A&M campus • Field phase: Oct. 2006 to Oct. 2007 in Brinkley, AR Experiments and ResultsSimulation on three birdsPhysical Experiment on Rock Pigeon Insects, falling leaves, other birds, etc.ROC
or
We will never post anything without your permission.
Don't have an account? Sign up