Giter Site home page Giter Site logo

enft-sfm's People

Contributors

ybbbbt avatar zjucvg avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

enft-sfm's Issues

GPU features

Dear,
Does this lib support any GPU option?
such as sift feature extraction, feature matching etc.

Thanks and Best Regards,
Wesley

How to visualize the result

Thank you for sharing this great project.
I build it from source on Ubuntu16.04, it rans well, but at last the result is save as result.act. I did not find any guide on how to visualize it, is there any way to transform it to PLY or OBJ format file?

running problem on ubuntu 16.04

When I run the program, I met the problem:
Loaded '../ENFT/param/param_ftr_tracking.txt'
Compile error:
ERROR: 0:1: '' : version '130' is not supported

zeros SIFT computed

Hello ZJU3DV,

I was trying your program on a Nvidia GTX 1070 for the Gangwan sequences. However, it extracted 0 SIFT features. Can you please provide a pointer on how to fix this problem?

Thank you!

Issues about running the demo on Ubuntu 16.04

Hello, I have runned the program on the Ubuntu 16.04 and got some output, but I'm comfused about the result and I don't know the meaning of the params in the output file, so is there any explaination about the v0-ftr.txt and v0.act files? and when running the program, the command line output is like the lines followed, and all of the frame feature match is failed, so I want to know if this is normal, and if not, how should I check this program. Very thanks,

Frame 400

SIFT features: 649

Frame (399, 400): 0 - 0 = 0 matches

Frame (398, 400): 0 - 0 = 0 matches
Frame (399, 400): 0 - 0 = 0 matches

SIFT matches: 0
ENFT matches: 0
Frame (398, 400) matches: 0
Frame (399, 400) matches: 0



Intrinsic Parameter: (750.00, 750.00, 479.50, 269.50)
Frames: Total = 401, Keyframe = 2, Solved = 0
Tracks: Total = 357751, Solved = 0, Inlier = 0
Measurements: Total = 357751, ENFT = 0, Outlier = 0
81.532(0.199x401) seconds, 4.92(5.03) fps
0.000000 second
0.000000 second
Saved '../Dataset/v0-ftr.txt'


Key frames: 401 --> 401
Key frame tracks: 4 --> 4
Clustering 0 points...
Floating point exception (core dumped)

Bug find

I changed 'config_plant.txt' file for image paths only. But it can not run out a result.
Bugs traces:
ENFT.cpp: ftrTracker.Run(V, useTmpFile ? outputDir + fileName : ""); -->
RunSequentialTracking(seq, fpTiming); -->
PushBackFrameAndFeatureMatches2(iFrmKey, iFrmCurrent, seq); -->
seq.MatchFrameFeatures(iFrm1, iFrm2, matches, m_marks1); -->
const TrackIndex *iTrks1 = GetFrameTrackIndexes(iFrm1), *iTrks2 = GetFrameTrackIndexes(iFrm2);

inline const TrackIndex *GetFrameTrackIndexes(const FrameIndex &iFrm) const {
return &m_mapMeaToTrk[m_mapFrmToMea[iFrm]]; // here
}

exception message is: expression:vector subscript out of range.

how to get point cloud and trajectory

hi, although I set view = 1, I still cannot get point cloud and trajectory, could you tell me how to get that please, and BTW, what is in the .act file and how to read that?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.