I've used Marziliano's[1] blur metric to reject images with motion blur recently. It is very fast and quite accurate in distinguishing blurred and non-blurred images.
Christian, please also be aware that some of the techniques do not incorporate changes in scale of the tracked object. If you are working with aerial footage then this might be an important consideration.
I've recently worked on a similar problem, so you need any help, please feel free to email me (email address is given in my profile)
There are visual tracking techniques that are not only more stable and robust that meanshift, but can also handle occlusions, adapt to changes in appearance models, etc. Have a look at the VOT challenge[1] for the state-of-art in visual tracking.
SEEKING WORK - Bangalore, India, Remote
Computer vision / image processing / machine learning / algorithms.
More than 9yrs of experience working on software research and development. Co-founded a tech startup, 2+yrs as a full-time freelancer.
Computer vision topics I've worked on: background subtraction, binary segmentation, facial expression transfer using active appearance models, object recognition, image restoration, projective geometry correction, object tracking, video stabilization, graphs cuts, face authentication, OCR pre-processing, gesture recognition, etc.
color: color quantization, color constancy (shadow removal), reduction to dominant color palette, illumination invariant color distance, color blending, color correction (gamut transform),
SEEKING WORK - Bangalore, India, Remote
Computer vision / image processing / machine learning / algorithms.
More than 9yrs of experience working on software research and development. Co-founded a tech startup, 2+yrs as a full-time freelancer.
Computer vision topics I've worked on: background subtraction, binary segmentation, facial expression transfer using active appearance models, object recognition, image restoration, projective geometry correction, object tracking, video stabilization, graphs cuts, face authentication, OCR pre-processing, gesture recognition, etc.
color: color quantization, color constancy (shadow removal), reduction to dominant color palette, illumination invariant color distance, color blending, color correction (gamut transform),
Learning topics: Classification: linear regression, LDA, SVM.
Clustering: KMeans, hierarchical kmeans, nearest neighbour.
Probabilitic analysis: naive bayes. Recommender systems.
Performance optimization: Speed up of background subtraction algorithms by writing optimized C code and SSE intrinsics.
More than 9yrs of experience working on software research and development. Co-founded a tech startup, 2+yrs as a full-time freelancer.
Computer vision topics I've worked on:
background subtraction, binary segmentation, facial expression transfer using active appearance models,
object recognition, image restoration, projective geometry correction, object tracking, video stabilization, graphs cuts, face authentication, OCR pre-processing, gesture recognition, etc.
color: color quantization, color constancy (shadow removal), reduction to dominant color palette, illumination invariant color distance, color blending, color correction (gamut transform),
Learning topics:
Classification: linear regression, LDA, SVM.
More than 9yrs of experience working on software research and development. Co-founded a tech startup, ~2yrs as a full-time freelancer.
Computer vision topics I've worked on: background subtraction, binary segmentation, facial expression transfer using active appearance models, object recognition, restoration, projective geometry correction, object tracking, video stabilization, graphs cuts, face authentication, OCR pre-processing, gesture recognition, etc.
color: color quantization, color constancy (shadow removal), reduction to dominant color palette, illumination invariant color distance, color blending, color correction (gamut transform),
Learning topics: Classification: linear regression, LDA,
SVM.
Clustering: KMeans, hierarchical kmeans, nearest neighbour. Probabilitic analysis: naive bayes.
Recommender systems.
Performance optimization: Speed up of background subtraction algorithms by writing optimized C code and SSE intrinsics.
More than 9yrs of experience working on software research and development. Have co-founded a tech startup. Working as freelancers for a couple of years, but can take up full-time work either as freelancer or employee.
Looking for an opportunities where I get to work on problems bigger than what I can take up if I were on my own. Do connect with me on linkedin, or by email.
More than 9yrs of experience working on software research and development. Co-founded a tech startup, ~2yrs as a full-time freelancer.
Computer vision topics I've worked on:
background subtraction, binary segmentation, facial expression transfer using active appearance models, object recognition, restoration, projective geometry correction, object tracking, video stabilization, graphs cuts, face authentication, OCR pre-processing, gesture recognition, etc.
color: color quantization, color constancy (shadow removal), reduction to dominant color palette, illumination invariant color distance, color blending, color correction (gamut transform),
SEEKING WORK in computer vision, machine learning. Remote or local to Bangalore, India.
8+ years experience, ex-cofounder of tech startup.
Freelancing for more than a year.
Topics I've worked on:
image binary segmentation, human body pose estimation, face tracking using AAM and warping, color blending, projective geometry, augmented reality, face authentication, change detection, OCR pre-processing, object detection, tracking and recognition, general classifications, etc.
Feel free to connect with me at:
linkedin: www.linkedin.com/in/link2hemangshah
email: hemang.j.shah at 'google's popular email service'
SEEKING WORK in computer vision & machine learning. Remote or local to Bangalore, India.
I've co-founded a startup, and have worked on various interesting & complex projects for more than 8yrs now. I love solving hard technical problems and on the other side, I can also contribute towards general understanding, viability and road maps of a business solution or towards solving a market requirement.
Feel free to connect with me at www.linkedin.com/in/link2hemangshah and contact me at hemang.j.shah at 'google's popular email service' dot com
SEEKING WORK in computer vision & machine learning.
Remote or local to Bangalore, India.
I've co-founded a startup, and have worked on various interesting & complex projects for more than 8yrs now. I love solving hard technical problems and on the other side, I can also contribute towards general understanding, viability and road maps of a business solution or towards solving a market requirement.
Feel free to connect with me at www.linkedin.com/in/link2hemangshah
and contact me at hemang.j.shah at 'google's popular email service' dot com
[1] http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.7.9...