Uploaded byLynda Hardman
Fish4Knowledge: large scale coral reef fish monitoring using undersea computer vision methods.
The Fish4Knowledge project utilizes undersea computer vision methods to monitor coral reef fish by collecting and analyzing video data from over 20,000 hours of footage. The project focuses on detecting fish species, assessing fish behaviors, and evaluating the accuracy of video analysis compared to expert evaluations. It features high-performance data platforms and aims to explore fish counts and species composition while addressing potential biases.
More Related Content
![Trinethorvaldsen[1]](https://cdn.slidesharecdn.com/ss_thumbnails/trinethorvaldsen1-120502022939-phpapp02-thumbnail.jpg?width=640&height=640&fit=bounds)
Similar to Fish4Knowledge: large scale coral reef fish monitoring using undersea computer vision methods.
Fish4Knowledge: large scale coral reef fish monitoring using undersea computer vision methods.
- 1. Fish4Knowledge Large scale coralreef fish monitoring using undersea computer vision methods Lynda Hardman CWI (Centrum Wiskunde&Informatica), Amsterdam, NL Centre for Mathematics & Computer Science
- 2. THE FISH4KNOWLEDGE PROJECT 1. CollectingVideo Data • Collecting videos • Detecting fish • Recognizing fish species • Recognizing fish behaviors • Evaluating video analysis accuracy 2. Exploring Video Data • Exploring fish counts • Investigating species composition • Checking potential biases 2fish4knowledge.eu
- 3. THE FISH4KNOWLEDGE PROJECT 1. CollectingVideo Data • Collecting videos • Detecting fish • Recognizing fish species • Recognizing fish behaviors • Evaluating video analysis accuracy 2. Exploring Video Data • Exploring fish counts • Investigating species composition • Checking potential biases 3fish4knowledge.eu
- 4. COLLECTING VIDEO DATA Multiple video streams: 9 Cameras, >20,000 hours of videos (Dec. 2012) Terabyte-scale data platform High-performance servers for data access 4fish4knowledge.eu
- 5. DETECTING FISH Detectionof fish in each frame Description of fish contour, color, texture... (>30 features) Tracking of single fish over several frames Handling partial and total occlusions Over 400 million fish detections 5fish4knowledge.eu
- 6. RECOGNIZING FISH SPECIES Detectionof body parts (head, tail…) Construction of a fish model for each species 15 species detected (96% of total number of fish)
- 7. RECOGNIZING FISH BEHAVIORS Detectionof behaviors by analyzing trajectories Relation to background objects (feeding, hiding…) Relation to other fish (pairing, grouping, solitary…) Fish Trajectories Description of scene’s background
- 8. THE FISH4KNOWLEDGE PROJECT 1. CollectingVideo Data • Collecting videos • Detecting fish • Recognizing fish species • Recognizing fish behaviors • Evaluating video analysis accuracy 2. Exploring Video Data • Exploring fish counts • Investigating species composition • Checking potential biases 8fish4knowledge.eu
- 9. EVALUATING VIDEO ANALYSIS ACCURACY 9fish4knowledge.eu Comparison with manual detections by experts Fish detection game to encourage crowd sourcing
- 10. EVALUATING VIDEO ANALYSIS ACCURACY Certainty Scores indicate the quality of each detection These can be used to filter out low-quality fish Score > 0.8 Fish Counts for 5 Certainty Score Thresholds Score > 0.2 Score > 0.4 Score > 0.5 Score > 0.6 Certainty Score: 0.4 Certainty Score: 0.9Certainty Score: 0.75 Certainty Score: 0.6
- 11. THE FISH4KNOWLEDGE PROJECT 1. CollectingVideo Data • Collecting videos • Detecting fish • Recognizing fish species • Recognizing fish behaviors • Evaluating video analysis accuracy 2. Exploring Video Data • Exploring fish counts • Investigating species composition • Checking potential biases 11fish4knowledge.eu
- 12.
- 13.
- 14. THE FISH4KNOWLEDGE PROJECT 1. CollectingVideo Data • Collecting videos • Detecting fish • Recognizing fish species • Recognizing fish behaviors • Evaluating video analysis accuracy 2. Exploring Video Data • Exploring fish counts • Investigating species composition • Checking potential biases 14fish4knowledge.eu
- 15. SPECIES COMPOSITION DEPENDS ONLOCATION
- 16. Amphiprionclarkii, Camera 38Plectroglyphidodondickii, Camera 39
- 17. SPECIES COMPOSITION DEPENDS ONLOCATION
- 18. THE FISH4KNOWLEDGE PROJECT 1. CollectingVideo Data • Collecting videos • Detecting fish • Recognizing fish species • Recognizing fish behaviors • Evaluating video analysis accuracy 2. Exploring Video Data • Exploring fish counts • Investigating species composition • Checking potential biases 18fish4knowledge.eu
- 19. SPECIES COMPOSITION DEPENDS ONLOCATION Plectroglyphidodondickii, Camera 38 Amphiprionclarkii, Camera 38 Plectroglyphidodondickii, Camera 39 Amphiprionclarkii, Camera 39
- 20. THE FISH4KNOWLEDGE PROJECT 20fish4knowledge.eu http://fish4knowledge.eu/people.htm Universityof Edinburgh (United Kingdom) Universitàdi Catania (Italy) Centrum Wiskunde&Informatica (Netherlands) National Applied Research Laboratories (Taiwan)
Editor's Notes
- #2 Good afternoon! As you may have noticed, I am not Bas Boom, but Lynda Hardman, and I’m not a marine biologist, I’m a computer scientist.I am at this conference, because I am a member of a European project that has spent the last 3 years building a system for automatically counting fish in fish videos.
- #17 Here you can see the habitats for camera 38, on the left, and camera 39, on the right (also based near Kenting).