张轶 博士/副教授/硕士生导师
研究方向：图像处理、模式识别、计算机视觉、人工智能
工作经历：
2000-2004：电子科技大学 本科
2004-2005：电子29所
2005-2010：National University of Singapore PhD
2009-2011：CE-Infosys, Singapore
2011-今： 四川大学
科研项目：
863面向动态场景感知应用示范（2012AA011804）
基于深度学习的跨域行人重识别及跟踪算法研究
干涉预警系统开发
精子密度仪开发
学术任职：担任Sensors副主编，参与IEEE TIP/TAES/TIM等期刊审稿工作。
专著(独作)：
《模式识别-数据质量视角》（15万字）
《信号处理中的机器学习算法》（20万字）
专利：
一种基于注意力机制的解耦表达国画生成方法，2022
一种基于深度学习的目标检测方法及系统，2021
基于激光雷达和惯导联合标定的同步定位与地图创建方法，2021
基于孪生网络的单目标跟踪方法，2021
基于特定标签和损失函数的孪生视觉跟踪方法，2021
一种基于深度学习的实时性道路图像语义分割方法及系统，2021
一种基于提取视频时空信息的人体行为识别方法及系统，2021
基于激光雷达与双目相机的定位与导航方法及装置，2020
一种相机、IMU和激光雷达联合的机器人定位方法，2020
一种新型汽车制动管路系统，2017
一种高速运动中用CCD是决定为装置，2017
一种自适应自动机械手结构，2017
一种新型汽车制动管路系统，2017
一种防止汽车带刹行驶的报警系统，2017
一种用于飞机上的对弹射座椅的姿态进行调整的系统，2017
一种用于飞机低能见度着陆的引导装置，2017
一种用于汽车驾驶的微抬头显示器，2014
部分论文（一作或通信）：
[1] A Dynamic Label Assignment Strategy for One-Stage Detectors. Neurocomputing, 2024
[3] Visual Tracking with Pyramidal Feature Fusion and Transformer based Model Predictor, Engineering Applications of Artificial Intelligence, 2024
[3] SiamRank: A Siamese based visual tracking network with ranking strategy. Pattern Recognition. 2023
[4] Learning Self-Correlation in Space and Time as Motion Representation for Action Recognition. IEEE Signal Processing Letters. 2023
[5] Knowledge Distillation for Object Detection based on Inconsistency-based Feature Imitation and Global Relation Imitation. Neurocomputing, 2024
[6] QPDet: A Queuing People Detector for Aerial Images. IEEE Geoscience and Remote Sensing letters. 2023
[7] Conv PVT: a fusion architecture of convolution and pyramid vision transformer. International Journal of Machine Learning and Cybernetics. 2022
[8] ESTI: an action recognition network with enhanced spatio-temporal information. International Journal of Machine Learning and Cybernetics, 2023
[9] RHL-track: Visual object tracking based on recurrent historical localization. Neural Computing and Applications. 2023
[10] A context- and level-aware feature pyramid network for object detection with attention mechanism. The Visual Computer. 2023
[11] CA-GAN: The Synthesis of Chinese Art Paintings using Generative Adversarial Networks. The Visual Computer. 2023
[12] Evota: An enhanced visual object tracking network with attention mechanism. Multimedia Tools and Applications. 2023
[13] LILO: A Novel Lidar–IMU SLAM System with Loop Optimization, IEEE Transactions on Aerospace and Electronic Systems, 2022
[14] IAMOT: Multi-Object Tracking with Integrated Heads and Attention Mechanism, Neurocomputing, 2022
[15] SiamET: a Siamese based visual tracking network with enhanced templates, Applied intelligence, 2022
[16] SiamOT: An Improved Siamese Network with Online Training for Visual Tracking, Sensors, 2022
[17] MEST: An Action Recognition Network with Motion Encoder and Spatio-Temporal Module, Sensors, 2022
[18] A Hierarchical Feature Extraction Network for Fast Scene Segmentation, Sensors, 2021
[19] Localization scheme based on key frame selection and a reliable plane using Lidar and IMU, Applied Optics, 2021
[20] Network Pruning for OCT Image Classification, MICCAI, 2019
[21] 3D Trajectory Reconstruction from Monocular Vision Based on Prior Spatial Knowledge, IEEE Sensors Journal, 2016
[22] Runway Extraction in Low Visibility Conditions Based on Sensor Fusion Method, IEEE Sensors Journal, 2014
[23] Sensor Fusion Method for Horizon Detection from an Aircraft in Low Visibility Conditions, IEEE Transactions on Instrumentation and Measurement, 2013
[24] Vision-Servo System for Automated Cell Injection, IEEE Transactions on Industrial Electronics, 2009
[25] Decoupled tracking and thermal monitoring of non-stationary targets, ISA Transaction, 2009
[26] Vision-assisted thermal monitoring system for CNC machine surveillance”, IEEE International Conference on Automation and Logistics, 2008 (Best Paper)
近年所带硕士生就业去向：
2020：南科大读博、腾讯、Dell
2021：快手、拼多多
2022：Intel、美团、电网、拼多多
2023: 选调、美团、快手、银行、美国读博
2024：选调、中电科、银行、转博
联系方式：
yi.zhang@scu.edu.cn
