In order to improve the performances of object detection and recognition, a two-stage framework combined with variable resolution control strategy is proposed. The images in low resolution and high resolution are employed in object detection and object recognition, respectively. Meanwhile, a feedback mechanism used in two-stage framework is proved to effectively improve the performances of object detection. The results show that under low resolution, the accuracy of object detection based on fixed resolution 320 × 240 without feedback mechanism is 36.7%. However, the accuracy of object detection of the proposed method based on variable resolution increases to 95.3%. Under high resolution, compared with the method based on fixed resolution 1280 × 960 using the two-stage framework, the time consumption of the proposed method with variable resolution decreases by 51.4%, while keeping almost identical recognition accuracy.
HuangSC.An advanced motion detection algorithm with video quality analysis for video surveillance systems. IEEE T Circ Syst Vid2011; 21: 1–14.
2.
HuangSCChenBH.Automatic moving object extraction through a real-world variable-bandwidth network for traffic monitoring systems. IEEE T Ind Electron2014; 61: 2099–2112.
3.
D’AgostinoCSaidiAScouarnecGet al. Learning-based driving events recognition and its application to digital roads. IEEE T Intell Transp2015; 16: 2155–2166.
4.
SunKWangZTuKet al. Recognition of mould colony on unhulled paddy based on computer vision using conventional machine-learning and deep learning techniques. Sci Rep2016; 6: 37994.
5.
SuYCHuangKYChenTWet al. A 52 mW full HD 160-degree object viewpoint recognition SoC with visual vocabulary processor for wearable vision applications. IEEE J Solid-St Circ2012; 47: 797–809.
6.
IngladaJ.Automatic recognition of man-made objects in high resolution optical remote sensing images by SVM classification of geometric image features. ISPRS J Photogramm2007; 62: 236–248.
7.
TutsoyOBrownM.Reinforcement learning analysis for a minimum time balance problem. T I Meas Control2016; 38: 1186–1200.
8.
SongHOGirshickRZicklerSet al. Generalized sparselet models for real-time multiclass object recognition. IEEE T Pattern Anal2015; 37: 1001–1012.
9.
SiddiquiAJMammeriABoukercheA.Real-time vehicle make and model recognition based on a bag of SURF features. IEEE T Intell Transp2016; 17: 3205–3219.
10.
MerinoMTNunezJ.Super-resolution of remotely sensed images with variable-pixel linear reconstruction. IEEE T Geosci Remote2007; 45: 1446–1457.
11.
AmiriMRabieeHR.RASIM: a novel rotation and scale invariant matching of local image interest points. IEEE T Image Process2011; 20: 3580–3591.
12.
MikolajczykKSchmidC.A performance evaluation of local descriptors. IEEE T Pattern Anal2005; 27: 1615–1630.
13.
LoweDG.Distinctive image features from scale-invariant keypoints. Int J Comput Vision2004; 60: 91–110.
14.
WuXWangXZhangJet al. Design of microcamera for field curvature and distortion correction in monocentric multiscale foveated imaging system. Opt Commun2017; 389: 189–196.
15.
FanFHaoQChengX.Retina-like sensor based on a lens array with a large field of view. Appl Optics2015; 54: 10692.
16.
SunHBZhaoHMMooneyPet al. A novel system for moving object detection using bionic compound eyes. J Bionic Eng2011; 8: 313–322.
17.
BelayGYOttevaereHMeuretYet al. Demonstration of a multichannel, multiresolution imaging system. Appl Optics2013; 52: 6081–6089.
18.
SongYMXieYZMalyarchukVet al. Digital cameras with designs inspired by the arthropod eye. Nature2013; 497: 95–99.
19.
KoHCStoykovichMPSongJZet al. A hemispherical electronic eye camera based on compressible silicon optoelectronics. Nature2008; 454: 748–753.
20.
LiuHPLiuYLSunFC.Traffic sign recognition using group sparse coding. Inform Sciences2014; 266: 75–89.
21.
CaoJHaoQPengYet al. Modeling and simulations of three-dimensional laser imaging based on space-variant structure. Opt Laser Technol2016; 78: 62–70.
22.
CaoJHaoQChengYet al. Modeling and simulations on retina-like sensors based on curved surface. Appl Optics2016; 55: 5738–5744.
23.
GonzálezMSánchez-PedrazaAMarfilRet al. Data-driven multiresolution camera using the foveal adaptive pyramid. Sensors2016; 16: E2003.
24.
WangTGaoHQiuJ.A combined fault-tolerant and predictive control for network-based industrial processes. IEEE T Ind Electron2016; 63: 2529–2536.
25.
WangTQiuJShenYet al. Performance-based adaptive fuzzy tracking control for networked industrial processes. IEEE T Cybernetics2016; 46: 1760–1770.
26.
WangTQiuJGaoHet al. Network-based fuzzy control for nonlinear industrial processes with predictive compensation strategy. IEEE T Syst Man Cy: S2017; 47(8): 2137–2147.
27.
LiHYWuCWFengZG.Fuzzy dynamic output-feedback control of non-linear networked discrete-time system with missing measurements. IET Control Theory A2015; 9: 327–335.
28.
WuLQiTFengZ.Average dwell time approach to L-2-L-infinity control of switched delay systems via dynamic output feedback. IET Control Theory A2009; 3: 1425–1436.
29.
NasibovHKholmatovAAkselliBet al. Performance analysis of the CCD pixel binning option in particle-image velocimetry measurements. IEEE/ASME T Mech2010; 15: 527–540.
30.
ZhouZPainBFossumER.Frame-transfer CMOS active pixel sensor with pixel binning. IEEE T Electron Dev1997; 44: 1764–1768.
31.
BorjiASihiteDNIttiL.Quantitative analysis of human-model agreement in visual saliency modeling: a comparative study. IEEE T Image Process2013; 22: 55–69.
WangJYangJYuKet al. Locality-constrained linear coding for image classification. In: Proceedings of the 2010 IEEE conference on computer vision and pattern recognition (CVPR), San Francisco, CA, 13–18 June 2010, pp.3360–3367. New York: IEEE.
34.
TutsoyO.Design and comparison base analysis of adaptive estimator for completely unknown linear systems in the presence of OE noise and constant input time delay. Asian J Control2016; 18: 1020–1029.
