Dr. Feng Zhu Profile

Dr. Feng Zhu

Professor at Shenyang Institute of Automation

SPIE Involvement:

Author

Publications (26)

Proceedings Article | 29 January 2024 Paper

A method for estimating the contribution of an object to scene semantics

Zhiyuan Lin, Feng Zhu, Jianyu Wang, Qun Wang, Pengfei Zhao

Proceedings Volume 12984, 1298408 (2024) https://doi.org/10.1117/12.3015832

Read Abstract +

Proceedings Article | 6 May 2019 Paper

A more repeatable and robust local reference frame for 3D local surface description

Rongrong Lu, Feng Zhu, Qingxiao Wu, Xingyin Fu

Proceedings Volume 11069, 1106913 (2019) https://doi.org/10.1117/12.2524177

KEYWORDS: Object recognition, 3D image processing, Principal component analysis, 3D modeling, 3D scanning

Read Abstract +

Proceedings Article | 6 May 2019 Paper

Efficient 3D correspondence grouping by two-stage filtering

Rongrong Lu, Feng Zhu, Qingxiao Wu, Yanzi Kong

Proceedings Volume 11069, 110690Z (2019) https://doi.org/10.1117/12.2524157

KEYWORDS: 3D modeling, 3D image processing, Clouds, Object recognition, 3D scanning

Read Abstract +

Proceedings Article | 12 December 2018 Paper

RGB-D dense SLAM with keyframe-based method

Xingyin Fu, Feng Zhu, Qingxiao Wu, Yunlei Sun

Proceedings Volume 10845, 108450J (2018) https://doi.org/10.1117/12.2505258

KEYWORDS: Cameras, Imaging systems, Systems modeling, Visualization, 3D modeling, Motion models, Associative arrays, Optimization (mathematics), Computing systems, Performance modeling

Read Abstract +

Proceedings Article | 12 December 2018 Paper

RGB-D dense mapping with feature-based method

Xingyin Fu, Feng Zhu, Qingxiao Wu, Rongrong Lu

Proceedings Volume 10845, 108450K (2018) https://doi.org/10.1117/12.2505305

KEYWORDS: Cameras, Imaging systems, Visualization, Associative arrays, Systems modeling, Matrices, Navigation systems, Autoregressive models, Visual process modeling, 3D modeling

Read Abstract +

Simultaneous Localization and Mapping (SLAM) plays an important role in navigation and augmented reality (AR) systems. While feature-based visual SLAM has reached a pre-mature stage, RGB-D-based dense SLAM becomes popular since the birth of consumer RGB-D cameras. Different with the feature-based visual SLAM systems, RGB-D-based dense SLAM systems, for example, KinectFusion, calculate camera poses by registering the current frame with the images raycasted from the global model and produce a dense surface by fusing the RGB-D stream. In this paper, we propose a novel reconstruction system. Our system is built on ORB-SLAM2. To generate the dense surface in real-time, we first propose to use truncated signed distance function (TSDF) to fuse the RGB-D frames. Because camera tracking drift is inevitable, it is unwise to represent the entire reconstruction space with a TSDF model or utilize the voxel hashing approach to represent the entire measured surface. We use moving volume proposed in Kintinuous to represent the reconstruction region around the current frame frustum. Different with Kintinuous which corrects the points with embedded deformation graph after pose graph optimization, we re-fuse the images with the optimized camera poses and produce the dense surface again after the user ends the scanning. Second, we use the reconstructed dense map to filter out the outliers of the features in the sparse feature map. The depth maps of the keyframes are raycasted from the TSDF volume according to the camera pose. The feature points in the local map are projected into the nearest keyframe. If the discrepancy between depth values of the feature and the corresponding point in the depth map exceeds the threshold, the feature is considered as an outlier and removed from the feature map. The discrepancy value is also combined with feature pyramid layer to calculate the information matrix when minimizing the reprojection error. The features in the sparse map reconstructed near the produced dense surface will impose large influence in camera tracking. We compare the accuracy of the produced camera trajectories as well as the 3D models to the state-of-the-art systems on the TUM and ICL-NIUM RGB-D benchmark datasets. Experimental results show our system achieves state-of-the-art results.

Proceedings Article | 12 December 2018 Paper

A novel ellipse detection method for real-time applications

Limin Zhang, Feng Zhu, Yingming Hao, Wang Pan

Proceedings Volume 10846, 1084626 (2018) https://doi.org/10.1117/12.2505381

KEYWORDS: Detection and tracking algorithms, Distance measurement, Machine vision, Computer vision technology, Digital image processing

Read Abstract +

Proceedings Article | 10 April 2018 Paper

LSAH: a fast and efficient local surface feature for point cloud registration

Rongrong Lu, Feng Zhu, Qingxiao Wu, Yanzi Kong

Proceedings Volume 10615, 106151G (2018) https://doi.org/10.1117/12.2303809

KEYWORDS: Clouds, Laser range finders, Feature extraction, Statistical modeling, Data modeling, 3D modeling, Image registration, 3D applications, Optical spheres, Performance modeling

Read Abstract +

SPIE Journal Paper | 27 December 2017

Three-dimensional object recognition using an extensible local surface descriptor

Rongrong Lu, Feng Zhu, Qingxiao Wu, Yingming Hao

OE, Vol. 56, Issue 12, 123109, (December 2017) https://doi.org/10.1117/12.10.1117/1.OE.56.12.123109

KEYWORDS: Detection and tracking algorithms, 3D modeling, Object recognition, Laser range finders, Optical spheres, Statistical modeling, Optical engineering, Data modeling, Clouds, Feature extraction

Read Abstract +

Proceedings Article | 21 July 2017 Paper

Signature of position angles histograms for 3D object recognition

Rongrong Lu, Feng Zhu, Yingming Hao, Huiying Cai, Yinshuai Zhao

Proceedings Volume 10420, 1042045 (2017) https://doi.org/10.1117/12.2281542

KEYWORDS: Object recognition

Read Abstract +

Proceedings Article | 23 April 2017 Paper

Gas pressure sensing based on antiresonant reflecting guidance hollow-core fiber

Maoxiang Hou, Yiping Wang, Feng Zhu, Ying Wang, Changrui Liao

Proceedings Volume 10323, 103231V (2017) https://doi.org/10.1117/12.2262316

KEYWORDS: Sensors, Cladding, Femtosecond phenomena, Waveguides, Magnetic sensors, Light sources, Spectrum analysis, Refraction, Fiber optics sensors, Micromachining

Read Abstract +

SPIE Journal Paper | 17 March 2017

Real-time depth camera tracking with geometrically stable weight algorithm

Xingyin Fu, Feng Zhu, Feng Qi, Mingming Wang

OE, Vol. 56, Issue 03, 033104, (March 2017) https://doi.org/10.1117/12.10.1117/1.OE.56.3.033104

KEYWORDS: Cameras, Detection and tracking algorithms, Imaging systems, 3D modeling, Optical tracking, Databases, Systems modeling, Performance modeling, Optical engineering, RGB color model

Read Abstract +

SPIE Journal Paper | 9 November 2016

Simple and efficient improvement of spin image for three-dimensional object recognition

Rongrong Lu, Feng Zhu, Yingming Hao, Qingxiao Wu

OE, Vol. 55, Issue 11, 113102, (November 2016) https://doi.org/10.1117/12.10.1117/1.OE.55.11.113102

KEYWORDS: 3D modeling, Object recognition, Laser range finders, 3D image processing, Detection and tracking algorithms, Data modeling, Optical engineering, Statistical modeling, Image resolution, Instrument modeling

Read Abstract +

Proceedings Article | 1 November 2016 Paper

An improved real-time visual tracking method for space non-cooperative target

Limin Zhang, Feng Zhu, Yingming Hao

Proceedings Volume 10157, 1015733 (2016) https://doi.org/10.1117/12.2247306

KEYWORDS: Optical tracking, 3D modeling, 3D acquisition, Statistical modeling, Visual process modeling

Read Abstract +

Proceedings Article | 25 October 2016 Paper

Shape matching under affine transformation using normalization and multi-scale area integral features

Huiying Cai, Feng Zhu, Yingming Hao, Rongrong Lu

Proceedings Volume 10157, 101571W (2016) https://doi.org/10.1117/12.2246696

Read Abstract +

Proceedings Article | 19 October 2016 Paper

Combining depth and gray images for fast 3D object recognition

Wang Pan, Feng Zhu, Yingming Hao

Proceedings Volume 10155, 101553C (2016) https://doi.org/10.1117/12.2247370

KEYWORDS: 3D image processing, Object recognition, Machine vision, Robotics

Read Abstract +

Proceedings Article | 8 October 2015 Paper

Performance evaluation of image enhancement methods for objects detection and recognition

Tiefeng Cai, Feng Zhu, Yingming Hao, Xiaopeng Fan

Proceedings Volume 9675, 96752Z (2015) https://doi.org/10.1117/12.2202949

KEYWORDS: Image enhancement, Image processing, Image contrast enhancement, Image compression, Information theory, Data processing, Image transmission, Image information entropy, Visual process modeling, Eye models

Read Abstract +

Proceedings Article | 24 November 2014 Paper

A new template matching method based on contour information

Huiying Cai, Feng Zhu, Qingxiao Wu, Sicong Li

Proceedings Volume 9301, 930109 (2014) https://doi.org/10.1117/12.2065931

KEYWORDS: Image processing, Machine vision, Computer vision technology, Process modeling, Pattern recognition, 3D vision, Object recognition, Hough transforms, Evolutionary algorithms, Neodymium

Read Abstract +

Template matching is a significant approach in machine vision due to its effectiveness and robustness. However, most of the template matching methods are so time consuming that they can’t be used to many real time applications. The closed contour matching method is a popular kind of template matching methods. This paper presents a new closed contour template matching method which is suitable for two dimensional objects. Coarse-to-fine searching strategy is used to improve the matching efficiency and a partial computation elimination scheme is proposed to further speed up the searching process. The method consists of offline model construction and online matching. In the process of model construction, triples and distance image are obtained from the template image. A certain number of triples which are composed by three points are created from the contour information that is extracted from the template image. The rule to select the three points is that the template contour is divided equally into three parts by these points. The distance image is obtained here by distance transform. Each point on the distance image represents the nearest distance between current point and the points on the template contour. During the process of matching, triples of the searching image are created with the same rule as the triples of the model. Through the similarity that is invariant to rotation, translation and scaling between triangles, the triples corresponding to the triples of the model are found. Then we can obtain the initial RST (rotation, translation and scaling) parameters mapping the searching contour to the template contour. In order to speed up the searching process, the points on the searching contour are sampled to reduce the number of the triples. To verify the RST parameters, the searching contour is projected into the distance image, and the mean distance can be computed rapidly by simple operations of addition and multiplication. In the fine searching process, the initial RST parameters are discrete to obtain the final accurate pose of the object. Experimental results show that the proposed method is reasonable and efficient, and can be used in many real time applications.

Proceedings Article | 24 November 2014 Paper

3D surface reconstruction from range slices

Mingming Wang, Feng Zhu, Ying-ming Hao

Proceedings Volume 9301, 93013G (2014) https://doi.org/10.1117/12.2073200

KEYWORDS: 3D image processing, Reconstruction algorithms, 3D image reconstruction, 3D modeling, Laser imaging, Image processing, Clouds, 3D displays, Imaging systems, 3D acquisition

Read Abstract +

Proceedings Article | 19 September 2013 Paper

A fast spin images matching method for 3D object recognition

Ming-ming Wang, Ying-ming Hao, Feng Zhu

Proceedings Volume 8905, 89052L (2013) https://doi.org/10.1117/12.2035012

KEYWORDS: 3D modeling, 3D image processing, Target recognition, Object recognition, 3D acquisition, Detection and tracking algorithms, Image processing, 3D imaging standards, Image filtering, Principal component analysis

Read Abstract +

Proceedings Article | 11 September 2013 Paper

A local image enhancement method based on adjacent pixel gray order-preserving principle

Xiaopeng Fan, Tiefeng Cai, Feng Zhu

Proceedings Volume 8907, 890723 (2013) https://doi.org/10.1117/12.2032922

KEYWORDS: Image processing, Image enhancement, Image quality, Image segmentation, Distortion, Visualization, Image contrast enhancement, Computer vision technology, Digital image processing, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 8 September 2011 Paper

Simulation of realistic infrared texture of aeolian sand ripples

Qian Liu, Feng Zhu, Xiao-wei Long, Ying-ming Hao, Shuang-fei Fu

Proceedings Volume 8193, 819308 (2011) https://doi.org/10.1117/12.896415

KEYWORDS: Infrared radiation, Infrared imaging, Thermography, Atmospheric modeling, Thermal modeling, Computer simulations, Thermodynamics, Solar radiation, Meteorology, Visualization

Read Abstract +

Proceedings Article | 9 December 2005 Paper

Analysis and design of a precise omnidirectional stereo vision optical device utilizing a single camera

Liancheng Su, Feng Zhu

Proceedings Volume 6024, 60241W (2005) https://doi.org/10.1117/12.666939

KEYWORDS: Mirrors, Cameras, Imaging systems, Calibration, Optical components, Combined lens-mirror systems, Sensors, Image processing, Stereo vision systems, Mirror pointing

Read Abstract +

Proceedings Article | 6 December 2005 Paper

Real time texture and global characters based station keeping for underwater vehicle

Xiaomin Liu, Feng Zhu, Yingming Hao, Jing Zhou

Proceedings Volume 6051, 605105 (2005) https://doi.org/10.1117/12.648901

KEYWORDS: Cameras, Imaging systems, Image processing, Visualization, Device simulation, Sensors, CCD cameras, Image analysis, Target detection, Servomechanisms

Read Abstract +

Proceedings Article | 25 September 2001 Paper

Three-dimensional visual methods for object pose measurement

Yingming Hao, Feng Zhu, Jinjun Ou

Proceedings Volume 4553, (2001) https://doi.org/10.1117/12.441551

KEYWORDS: Visual process modeling, Model-based design, 3D modeling, Visualization, Cameras, 3D metrology, Quantization, 3D vision, Mobile robots, Imaging systems

Read Abstract +

Proceedings Article | 9 May 2000 Paper

Information processing techniques based on vision location

Yingming Hao, Zaili Dong, Feng Zhu

Proceedings Volume 4077, (2000) https://doi.org/10.1117/12.385614

Read Abstract +

Proceedings Article | 25 September 1998 Paper

Spectral-analysis-based range image acquiring method

Yingming Hao, Feng Zhu, Xinping Xu

Proceedings Volume 3545, (1998) https://doi.org/10.1117/12.323638

KEYWORDS: Calibration, 3D image processing, Cameras, 3D modeling, Light, Imaging systems, Image classification, Light sources, Image processing, Structured light

Read Abstract +

Showing 5 of 26 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years