Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
OpenTalks.AI - Дмитрий Пагин, Fast cars detecti...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
OpenTalks.AI
February 21, 2020
Science
2.2k
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
OpenTalks.AI - Дмитрий Пагин, Fast cars detection and traffic estimation
OpenTalks.AI
February 21, 2020
Transcript
37 slides
Fast cars detection and traffic estimation Dmitriy Pagin, ML and
CV developer
Task Road traffic analysis in Russia is manual. It takes
more than 8 hours for 15 minutes video today
Task • detect cars
Task • detect cars • track cars
Baseline - people tracking
Problems Cars: - faster (2 metres per frame!) - smaller
(10 px in minimal dimension) + more predictable movement
YOLOv2 - blinking - problems on small cars - problems
on edges
YOLOv2 1 fps
YOLOv3 - bigger + accurate on small + fullHD frame
+ robust
YOLOv3 7 fps
> 70k cars on 4k images Dataset
better than 1024x1024x1 Learning and Fine-tuning - 608x608 px -
batchSize = 3 - custom augmenters
None
Learning and Fine-tuning - 608x608 px - batchSize = 3
- custom augmenters - Radam optimizer (instead warmup + reduce LR) - Hard negative mining for trucks
Learning and Fine-tuning - 608x608 px - batchSize = 3
- custom augmenters - Radam optimizer (instead warmup + reduce LR) - Hard negative mining for trucks mAP75 = 0.96
Baseline Inference Speed 7 fps
Weights Pruning
Weights Pruning -25% convs = size: 240 mb mAp: 0.9656
inf: 150 ms size: 155 mb mAp: 0.9622 inf: 100 ms 10 fps
OpticalFlow step or classical cv is alive ! - find
good features to track - calculate sparse optical flow
OpticalFlow step 19 fps Calculation doesnt work for 3 consistent
frames
Speed extrapolation step - estimate speed as pixels/frame - extrapolate
next position 28 fps
Final pipeline 1 2 3 4 5 6 Update trajectories
4 5 6 step 1 step 2 Speed Extrapolation OpticalFlow YOLOv3 Detection Engine
1 fps -> 28 fps on FULLHD
Tracking - IoU - Color descriptor (it’s enough!)
Bridges! - Allowed zone by motion vector - Size overlap
- Color descriptor
Bridges! - Allowed zone by motion vector - Size overlap
- Color descriptor
Thanks! Questions?
[email protected]
+7 952 335 65 70
Appendix. Examples
Appendix. Examples
Appendix. Examples
Appendix. Yolov3
Weights Pruning Шаг mAP75 Число параметров, млн Размер сети, мб
От изначальной, % Время прогона, мс Условие обрезания 0 0.965 60 241 100 150 - 1 0.962 55 218 91 140 5% от всех 2 0.962 50 197 83 132 5% от всех 3 0.963 39 155 64 112 15% для слоев с 400+ сверток 4 0.955 31 124 51 100 10% для слоев с 100+ сверток
Appendix. Radam
Pruning convs
Pruning convs. Good choice 2000
Pruning convs. Bad choice 25
Pruning flat
More Decks by OpenTalks.AI
See All by OpenTalks.AI
OpenTalks.AI - Виктор Лемпицкий, Моделирование 3Д сцен: новые подходы в 2020 году
opentalks
0
510
OpenTalks.AI - Алексей Чернявский, Нейросетевые алгоритмы для повышения качества медицинских изображений
opentalks
0
460
OpenTalks.AI - Александр Громов, Устойчивость нейросетевых моделей при анализе КТ/НДКТ-исследований
opentalks
0
390
OpenTalks.AI - Денис Тимонин, Megatron-LM: Обучение мультимиллиардных LMs при помощи техники Model Parallelism
opentalks
0
550
OpenTalks.AI - Егор Филимонов, Возможности платформы Huawei Atlas и эффективный гетерогенный инференс.
opentalks
0
200
OpenTalks.AI - Александр Прозоров, Референсная архитектура робота сервисного центра в отраслях с изменчивыми бизнес-процессами
opentalks
0
410
OpenTalks.AI - Наталья Лукашевич, Анализ тональности по отношению к компании — с чем не справился BERT
opentalks
0
350
OpenTalks.AI - Константин Воронцов, Фейковые новости и другие типы потенциально опасного дискурса: типология, подходы, датасеты, соревнования
opentalks
0
470
OpenTalks.AI - Дмитрий Ветров, Фрактальность функции потерь, эффект двойного спуска и степенные законы в глубинном обучении - фрагменты одной мозаики
opentalks
0
510
Other Decks in Science
See All in Science
人工知能のための哲学塾 ニューロフィロソフィ篇 第一夜 「無著、世親と唯識のはじまり、ニューラルネットワークのはじまり」
miyayou
0
150
自社のレビュー履歴からAIコードレビュアーをつくる方法
estie
5
2k
Cross-Media Technologies, Information Science and Human-Information Interaction
signer
PRO
3
33k
明治薬科大学講義_ビッグデータ解析を支えるデータベース技術とクラウドコンピューティング
ktatsuya
1
220
AI Agents for Earth Observation
sabman
0
150
Toward Causal Scientific Discovery with AI
sshimizu2006
0
250
JSAI2026企画セッションKS-14 インタビュー集『⼈⼯知能と哲学と四つの問い』が提起する⼈⼯知能のこれからの課題 趣旨説明 / JSAI2026 Special Session: A Collection of Interviews, “Artificial Intelligence, Philosophy, and Four Questions”
ykiyota
0
500
JPA2026_NetworkSymposium_Kashihara
junkashihara
0
130
[Webinaire presse] Sécheresse 2026 : quelles conséquences techniques en élevage de ruminants et quels leviers d'action ?
institutdelelevage
PRO
0
390
データベース04: SQL (1/3) 単純質問 & 集約演算
trycycle
PRO
0
1.8k
生成AI時代のインタラクションサイエンス(招待講演)/interaction-science
okana2ki
0
130
AlgorithAlgorihms for Decision Making
mickey_kubo
0
200
Featured
See All Featured
Paper Plane (Part 1)
katiecoart
PRO
3
12k
svc-hook: hooking system calls on ARM64 by binary rewriting
retrage
2
680
Game over? The fight for quality and originality in the time of robots
wayneb77
1
330
brightonSEO & MeasureFest 2025 - Winning Strategies for Black Friday CRO & PPC - Christian Goodrich
cargoodrich
3
900
Ten Tips & Tricks for a 🌱 transition
stuffmc
1
290
Building Adaptive Systems
keathley
44
3.3k
Kristin Tynski - Automating Marketing Tasks With AI
techseoconnect
PRO
0
590
Utilizing Notion as your number one productivity tool
mfonobong
4
640
Being A Developer After 40
akosma
PRO
92
590k
What Being in a Rock Band Can Teach Us About Real World SEO
427marketing
0
1.1k
Dominate Local Search Results - an insider guide to GBP, reviews, and Local SEO
greggifford
PRO
0
400
Building a A Zero-Code AI SEO Workflow
portentint
PRO
0
830