Vehicle Detection Method in UAV Aerial Video

doi:10.16182/j.issn1004731x.joss.201807043

Abstract

Abstract: The use of UAV aerial photography to obtain traffic information has many advantages like a flexible high mobility, comprehensive information and so on, which plays a vital role in the emergency response, anti-terrorism/battlefield and other environments. This paper proposes a method for vehicle detection in UAV aerial video. Aiming at the problem of UAV video image deflection, the image registration method based on SURF algorithm is used to correct the deflection of UAV hatching video according to the standard frame. The background and the moving vehicle are separated by the pixel-based adaptive segmentation algorithm to detect the moving vehicle in the video. Experiments show that the matching accuracy of our method rate up to 90%, and can detect the movement of vehicles accurately in a large range of scenes, whose recall(Re), precision(Pr), false negative rate (FNR) are 82.3%, 90.1%, 17.3%.

Key words: unmanned aerial vehicle, SURF algorithm, image matching, moving vehicle detection

CLC Number:

TP391

Wang Suqin, Shi Wenhao, Li Zhaoxin, Mao Tianlu. Vehicle Detection Method in UAV Aerial Video[J]. Journal of System Simulation, 2018, 30(7): 2776-2786.

References

[1] Lowe D G.Object Recognition from Local Scale-Invariant Features[J]. International Conference on Computer Vision, IEEE, 1999 , 2(3) :1150-1157.
[2] Lowe D G.Distinctive image features fi'om scale- invariant keypoints[J]. International Journal of Computer Vision(S0920-5691), 2004, 60(2): 91-110.
[3] Ke Y, Sukthankar R.PCA-SIFT: A More Distinctive Representation for Local Image Descriptors[C]//IEEE Computer Society Conference on Computer Vision & Pattern Recognition. IEEE Computer Society, 2004: 506-513.
[4] Mikolajczyk K, Schmid C.A Performance Evaluation of Local Descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S1939-3539), 2005, 27(10): 1615-1630.
[5] Delponte E, Isgrò F, Odone F, et al.SVD-matching using SIFT features[J]. Graphical Models(S1524-0703), 2006, 68(5/6): 415-431.
[6] Grabner M, Grabner H, Bischof H.Fast approximated SIFT[C]//Asian Conference on Computer Vision. Springer-Verlag, 2006: 918-927.
[7] Bay H, Tuytelaars T, Gool L V.SURF: Speeded Up Robust Features[J]. Computer Vision & Image Understanding(S1077-3142), 2006, 110(3): 404-417.
[8] Cheng P, Zhou G, Zheng Z.Detecting and counting vehicles from small low -cost UAV images[C]//ASPRS 2009 Annual Conference. Baltimore, Maryland, 2009: 1-7.
[9] Azevedo C L, Cardoso J L, Ben-Akiva M, et al.Automatic Vehicle Trajectory Extraction by Aerial Remote Sensing[J]. Procedia - Social and Behavioral Sciences(S1877-0428), 2014, 111(111): 849-858.
[10] Gupte S, Masoud O, Martin R F K, et al. Detection and classification of vehicles[J]. IEEE Transactions on Intelligent Transportation Systems(S1524-9050), 2002, 3(1): 37-47.
[11] Sivaraman S, Trivedi M M.Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis[J]. IEEE Transactions on Intelligent Transportation Systems(S1524-9050), 2013, 14(4):1773-1795.
[12] Machida T, Naito T.GPU & CPU cooperative accelerated pedestrian and vehicle detection[C]//IEEE International Conference on Computer Vision Work shops. IEEE, 2011: 506-513.
[13] Liu W, Wen X Z, Duan B, et al.Rear Vehicle Detection and Tracking for Lane Change Assist[C]//Intelligent Vehicles Symposium. IEEE, 2007: 252-257.
[14] Sivaraman S, Trivedi M M.A General Active-Learning Framework for On-Road Vehicle Recognition and Tracking[J]. IEEE Transactions on Intelligent Transportation Systems(S1524-9050), 2010, 11(2): 267-276.
[15] Wang C C R, Lien J J J. Automatic Vehicle Detection Using Local Features-A Statistical Approach[J]. IEEE Transactions on Intelligent Transportation Systems (S1524-9050), 2008, 9(1): 83-96.
[16] Lin B F, Chan Y M, Fu L C, et al.Integrating Appearance and Edge Features for Sedan Vehicle Detection in the Blind-Spot Area[J]. IEEE Transactions on Intelligent Transportation Systems (S1524-9050), 2012, 13(2): 737-747.
[17] Tehrani Niknejad H, Takeuchi A, Mita S, et al.On-Road Multivehicle Tracking Using Deformable Object Model and Particle Filter With Improved Likelihood Estimation[J]. IEEE Transactions on Intelligent Transportation Systems (S1524-9050), 2012, 13(2): 748-758.
[18] Nandyal M S, Patil P.VEHICLE DETECTION AND TRAFFIC ASSESSMENT USING IMAGES[J]. International Journal of Computer Science & Mobile Computing (S2320-088X), 2013, 2(9).
[19] Ozkurt C, Camci F.Automatic Traffic Density Estimation and Vehicle Classification for Traffic Surveillance Systems Using Neural Networks[J]. Mathematical & Computational Applications(S1300-686X), 2009, 14(3): 187-196.
[20] Mikolajczyk K, Schmid C.Scale & Affine Invariant Interest Point Detectors[J]. International Journal of Computer Vision(S0920-5691), 2004, 60(1): 63-86.
[21] Hofmann M, Tiefenbacher P, Rigoll G.Background segmentation with feedback: The Pixel-Based Adaptive Segmenter[C]//Computer Vision and Pattern Recognition Workshops. IEEE, 2012: 38-43.