Kan Ouivirach, Ph.D.
Pak Kret, Nonthaburi, Thailand
1K followers
500+ connections
About
Activity
-
Data engineers, DON'T GET OVERWHELMED by alerts and notifications! Here is a better way to avoid driving crazy with Airflow 👇 The Notifiers! And…
Data engineers, DON'T GET OVERWHELMED by alerts and notifications! Here is a better way to avoid driving crazy with Airflow 👇 The Notifiers! And…
Liked by Kan Ouivirach, Ph.D.
Experience & Education
Licenses & Certifications
Volunteer Experience
-
Community Organizer
Data Council
- Present 5 years 9 months
Science and Technology
Build the top community of data influencers!
Reference: https://medium.com/@petesoder/why-we-became-data-council-1-14-19-b7c29c49c823 -
CoRise Ambassador
co:rise
- Present 2 years 2 months
Science and Technology
co:rise brings the best of the in-person learning context to eLearning. Meet and interact with your instructors, fellow classmates, and other field experts in a mix of synchronous and asynchronous study sessions, lectures, fireside chats, and assignments. If you've ever felt isolated or frustrated due to the lack of interactivity in other eLearning contexts, try a course at co:rise and see the benefits of learning in a group setting with other invested professionals.
Having benefited…co:rise brings the best of the in-person learning context to eLearning. Meet and interact with your instructors, fellow classmates, and other field experts in a mix of synchronous and asynchronous study sessions, lectures, fireside chats, and assignments. If you've ever felt isolated or frustrated due to the lack of interactivity in other eLearning contexts, try a course at co:rise and see the benefits of learning in a group setting with other invested professionals.
Having benefited from previous courses and the co:rise community, I'm part of a group of alumni (co:risers) that promote the platform to future students and interact with current students. -
Co Lead
Facebook Developer Circle: Bangkok
- 3 years 2 months
Science and Technology
-
Community Organizer
Girls Who Dev
- Present 9 years
-
Community Organizer
PyLadies Bangkok
- Present 5 years
-
Mentor
Django Girls
- Present 6 years 6 months
Science and Technology
Saturday, 24 March 2018 - https://djangogirls.org/bangkok/
-
Writer
Thai Programmer Organization
- 5 years 4 months
Science and Technology
Publications
-
Extracting the Object from the Shadows: Maximum Likelihood Object/Shadow Discrimination
ECTI-CON
We propose and experimentally evaluate a new method for detecting shadows using a simple maximum likelihood formulation based on color information. We first estimate, offline, a joint probability distribution over the difference in the HSV color space between pixels in the current frame and the corresponding pixels in a background model, conditional on whether the pixel is an object pixel or a shadow pixel. Given the learned distribution, at run time, we use the maximum likelihood principle to…
We propose and experimentally evaluate a new method for detecting shadows using a simple maximum likelihood formulation based on color information. We first estimate, offline, a joint probability distribution over the difference in the HSV color space between pixels in the current frame and the corresponding pixels in a background model, conditional on whether the pixel is an object pixel or a shadow pixel. Given the learned distribution, at run time, we use the maximum likelihood principle to classify each foreground pixel as either shadow or object. In an experimental evaluation, we find that the method outperforms standard methods on three different real-world video surveillance data sets. We conclude that the proposed shadow detection method would be an extremely effective component in an intelligent video surveillance system.
Other authorsSee publication -
Automatic Suspicious Behavior Detection from a Small Bootstrap Set
VISAPP
A new method for automatic identification of suspicious behavior in video surveillance data. The approach works by constructing scene-specific statistical models explaining the behaviors occurring in a small bootstrap data set. It partitions the bootstrap set into clusters then assigns new observation sequences to clusters based on statistical tests of HMM log likelihood scores.
Other authorsSee publication -
Incremental Behavior Modeling and Suspicious Activity Detection
Pattern Recognition
We propose and evaluate an efficient method for automatic identification of suspicious behavior in video surveillance data that incrementally learns scene-specific statistical models of human behavior without requiring storage of large databases of training data. The approach begins by building an initial set of models explaining the behaviors occurring in a small bootstrap data set. The bootstrap procedure partitions the bootstrap set into clusters then assigns new observation sequences to…
We propose and evaluate an efficient method for automatic identification of suspicious behavior in video surveillance data that incrementally learns scene-specific statistical models of human behavior without requiring storage of large databases of training data. The approach begins by building an initial set of models explaining the behaviors occurring in a small bootstrap data set. The bootstrap procedure partitions the bootstrap set into clusters then assigns new observation sequences to clusters based on statistical tests of HMM log likelihood scores. Cluster-specific likelihood thresholds are learned rather than set arbitrarily. After bootstrapping, each new sequence is used to incrementally update the sufficient statistics of the HMM it is assigned to. In an evaluation on a real-world testbed video surveillance data set, we find that within one week of observation, the incremental method's false alarm rate drops below that of a batch method on the same data. The incremental method obtains a false alarm rate of 2.2% at a 91% hit rate. The method is thus a practical and effective solution to the problem of inducing scene-specific statistical models useful for bringing suspicious behavior to the attention of human security personnel.
Other authorsSee publication -
Clustering Human Behaviors with Dynamic Time Warping and Hidden Markov Models for a Video Surveillance System
ECTI-CON
A new method for clustering human behaviors that is suitable for bootstrapping an anomaly detection module for intelligent video surveillance systems. The method uses dynamic time warping, agglomerative hierarchical clustering, and hidden Markov models to provide an initial partitioning of a set of observation sequences then automatically identifies where to cut off the hierarchical clustering dendrogram.
Other authorsSee publication
Projects
-
Scantron
-
Developed computer vision algorithms in C/C++ using OpenCV for an answer sheet checking and scoring for each answer sheet by using a scanned image of an answer sheet.
Note: This project was funded by MakeSense IT company.Other creatorsSee project
Languages
-
Thai
-
-
English
-
More activity by Kan
-
158 countries, 41 languages. Look at this 👇 Airflow is a global community-based open-source project. It has a massive community and is powered by…
158 countries, 41 languages. Look at this 👇 Airflow is a global community-based open-source project. It has a massive community and is powered by…
Liked by Kan Ouivirach, Ph.D.
-
SQL is conquering the world! (already did?) Look at that 😳👇 Infrastructure as SQL I didn't even know about it, and it looks pretty insane! For…
SQL is conquering the world! (already did?) Look at that 😳👇 Infrastructure as SQL I didn't even know about it, and it looks pretty insane! For…
Liked by Kan Ouivirach, Ph.D.
-
With the latest announcements of Databricks acquiring Tabular, the company behind Apache Iceberg, many are asking about the differences between…
With the latest announcements of Databricks acquiring Tabular, the company behind Apache Iceberg, many are asking about the differences between…
Liked by Kan Ouivirach, Ph.D.
-
Our upcoming O'Reilly book, Implementing Data Mesh, has now completed the technical review phase! And that means that we (my co-author, Jean-Georges…
Our upcoming O'Reilly book, Implementing Data Mesh, has now completed the technical review phase! And that means that we (my co-author, Jean-Georges…
Liked by Kan Ouivirach, Ph.D.
-
NEW VIDEO 🥳 Everything you need to backfill your DAGs in Airflow properly 👇 Backfilling data is .. unfortunately .. part of our data engineering…
NEW VIDEO 🥳 Everything you need to backfill your DAGs in Airflow properly 👇 Backfilling data is .. unfortunately .. part of our data engineering…
Liked by Kan Ouivirach, Ph.D.
-
💡 Some very useful #dbt packages part 2. In this post, I want to highlight some packages developed by the community. Let me know if you use some of…
💡 Some very useful #dbt packages part 2. In this post, I want to highlight some packages developed by the community. Let me know if you use some of…
Liked by Kan Ouivirach, Ph.D.
-
STOP using the PostgresOperator (or the other dbOperators) ❌ There is one operator to rule them all 👇 The SQLExecuteQueryOperator 😍 Why? Having…
STOP using the PostgresOperator (or the other dbOperators) ❌ There is one operator to rule them all 👇 The SQLExecuteQueryOperator 😍 Why? Having…
Liked by Kan Ouivirach, Ph.D.
-
สุดยอด Athibet Prawane #ODDS https://lnkd.in/g3FYdp85
สุดยอด Athibet Prawane #ODDS https://lnkd.in/g3FYdp85
Shared by Kan Ouivirach, Ph.D.
-
Have you heard of Pathway? It’s a Python ETL framework with a Rust engine. They started as a Python stream processing alternative to Flink, Kafka…
Have you heard of Pathway? It’s a Python ETL framework with a Rust engine. They started as a Python stream processing alternative to Flink, Kafka…
Liked by Kan Ouivirach, Ph.D.
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More