Page 136 - 《武汉大学学报(信息科学版)》2025年第10期
P. 136

第 50 卷第 10 期                卢朝晖等:交通目标特定区域的图像质量评估                                     2071


                    XU Junwei,LIU Yongsheng,WU Da,et al. De‑         Image  Quality  Assessment  via  Non-Local  Depen‑
                    velopment and Outlook of Monitoring and Measuring   dency  Modeling[C]//The  24th  International  Work‑
                    Technologies of Tunnel and Underground Engineering  shop  on  Multimedia  Signal  Processing,  Shanghai,
                    [J]. Journal of Geomatics,2023,48(3):7-13.       China, 2022.
               [3]  张雪, 郭佳昕 .  监控视频下的人脸图像质量分析技                  [14]  GOODFELLOW  I,  POUGET-ABADIE  J,  MIR‑
                    术[J].  计算机系统应用, 2022, 31(9): 313-318.            ZA  M,  et  al.   Generative  Adversarial  Nets[C]//
                    ZHANG Xue, GUO Jiaxin.  Quality Analysis Tech‑   The  28th  International  Conference  on  Neural  Infor‑
                    nology  for  Face  Images  in  Surveillance  Videos[J].    mation  Processing  Systems,  Montreal,  Quebec,
                    Computer Systems and Applications, 2022, 31(9):   Canada, 2014.
                    313-318.                                    [15]  LI  X  L,  LI  G,  ZHANG  E  Q,  et  al.   Determinant
               [4]  WANG  Z,  BOVIK  A  C.   Reduced-  and  No-Reference   Point  Process  Sampling  Method  for  Text-to-Image
                    Image  Quality  Assessment[J].   IEEE  Signal  Processing   Generation[J].   Geomatics  and  Information  Science
                    Magazine, 2011, 28(6): 29-40.                    of Wuhan University , 2024, 49(2): 246-255.
               [5]  TAO  S,  HE  R  Z,  DAI  L  S,  et  al.   MD-IQA:   [16]  SIMONYAN K, ZISSERMAN A.  Very Deep Con‑
                    Learning  Multi-scale  Distributed  Image  Quality  As‑  volutional Networks for Large-Scale Image Recogni‑
                    sessment  with  Semi  Supervised  Learning  for  Low   tion[C]//The 3rd International Conference on Lear‑
                    Dose  CT[EB/OL].  (2023-11-14)[2024-01-05].      ning Representations,San Diego,CA,USA,2015.
                    https://arxiv. org/abs/2311. 08024.         [17]  GHADIYARAM D, BOVIK A C.  Massive Online
               [6]  MOHAMMADI S, ASCENSO J.  Predictive Sam‑         Crowdsourced Study of Subjective and Objective Pic‑
                    pling for Efficient Pairwise Subjective Image Quality   ture  Quality[J].   IEEE  Transactions  on  Image  Pro‑
                    Assessment[C]//The 31st ACM International Con‑   cessing, 2016, 25(1): 372-387.
                    ference on Multimedia, Ottawa , Canada, 2023.  [18]  VIRTANEN  T,  NUUTINEN  M,  VAAHTER‑
               [7]  MITTAL  A,  MOORTHY  A  K,  BOVIK  A  C.         ANOKSA  M,  et  al.   CID2013:  A  Database  for
                    No-Reference Image Quality Assessment in the Spa‑  Evaluating  No-Reference  Image  Quality  Assess‑
                    tial  Domain[J].   IEEE  Transactions  on  Image  Pro‑  ment Algorithms[J].  IEEE Transactions on Image
                    cessing, 2012, 21(12): 4695-4708.                Processing, 2015, 24(1): 390-402.
               [8]  MITTAL  A,  SOUNDARARAJAN  R,  BOVIK  A     [19]  BOCHKOVSKIY A, WANG C Y, LIAO H Y M.
                    C.  Making a “Completely Blind” Image Quality Ana‑  YOLOv4:  Optimal  Speed  and  Accuracy  of  Object
                    lyzer[J].  IEEE Signal Processing Letters, 2013, 20  Detection [M].   (2020-04-23) [2024-01-05].
                    (3): 209-212.                                    https://arxiv. org/abs/2004. 10934.
               [9]  ZHANG W X, MA K D, YAN J, et al.  Blind Image   [20]  XU Z, YANG W, MENG A, et al.  Towards End-
                    Quality  Assessment  Using  a  Deep  Bilinear  Convolu‑  to-End License Plate Detection and Recognition: A
                    tional Neural Network[J].  IEEE Transactions on Cir‑  Large  Dataset  and  Baseline [C]//The  European
                    cuits  and  Systems  for  Video  Technology,  2020,  30  Conference  on  Computer  Vision,  Munich,  Germa‑
                    (1): 36-47.                                      ny, 2018.
               [10]  KE  J  J,  WANG  Q  F,  WANG  Y  L,  et  al.   MU‑  [21]  NAVARRO  G.   A  Guided  Tour  to  Approximate
                    SIQ: Multi-scale Image Quality Transformer[C]//  String  Matching[J].   ACM  Computing  Surveys,
                    IEEE/CVF  International  Conference  on  Computer   2001, 33(1): 31-88.
                    Vision, Montreal, QC, Canada, 2021.         [22]  SPRENT P. Applied Nonparametric Statistics [M].
               [11]  YING  Z  Q,  NIU  H  R,  GUPTA  P,  et  al.   From   New  York:  Springer  Science  &  Business  Media,
                    Patches to Pictures (PaQ-2-PiQ): Mapping the Per‑  2012.
                    ceptual  Space  of  Picture  Quality[C]//IEEE/CVF   [23]  KINGMA  D  P,  BA  J.   Adam:  A  Method  for  Sto‑
                    Conference on Computer Vision and Pattern Recog‑  chastic Optimization[C]//The 3rd International Con‑
                    nition, Seattle, WA, USA, 2020.                  ference  for  Learning  Representations,  San  Diego,
               [12]  SUN  S  M,  YU  T,  XU  J  H,  et  al.   GraphIQA:   CA,USA, 2015.
                    Learning Distortion Graph Representations for Blind   [24]  HE  K,  ZHANG  X,  REN  S,  et  al.   Deep  Residual
                    Image  Quality  Assessment[J].   IEEE  Transactions   Learning  for  Image  Recognition[C]//IEEE/CVF

                    on Multimedia, 2022, 25: 2912-2925.              Conference on Computer Vision and Pattern Recog‑
               [13]  JIA  S,  CHEN  B  L,  LI  D  Q,  et  al.   No-Reference   nition, Las Vegas, NV, USA, 2016.
   131   132   133   134   135   136   137   138   139   140   141