Checklist NTO AI 2025 Stage 1 (qualifying), engineering tour · 2.4.1 task
Multi-class Classification of Animals in Camera-trap Photos
Russian title: Многоклассовая классификация животных по фото с фотоловушек
Classify camera-trap photos of wild animals into ten groups of biologically similar species.
The task
Using camera-trap images supplied by partner research organisations, participants classify wild animals into enlarged groups of similar species, reducing the effort of manual species recognition. The data include small parts of animals and night or blurred photos; labels were assigned by wildlife-monitoring researchers.
Groups: 0 hare, 1 wild boar, 2 cats, 3 mustelids, 4 bear, 5 deer, 6 panthers, 7 bovids, 8 canids, 9 marmot. The split is about 70% train / 30% test, and the test set about 40% public / 60% private.
Abridged and translated by SOTA from the official Russian materials. The official statement has the exact rules, and it wins wherever this summary differs.
In English
This task was published in Russian. SOTA translated its 2 files into English on 16 September 2026. Only the words changed in the notebooks: markdown, code comments, messages and printed output. The code, file names and paths are the original's, so a translated notebook runs with the original data.
- Task statement Russian original of Task statement
- Baseline notebook Russian original of Baseline notebook
Read the task statement in English
Multi-class Classification of Animals in Camera-trap Photos
English translation by SOTA – AI Community of the Russian original. Organisers who would like this translation removed can email [email protected].
Source: the 2024/25 task collection of the National Technology Olympiad (NTO), "Artificial Intelligence" profile, Stage 1, pp. 99–101: original PDF.
2.4. Engineering tour
The aim of the task is to test the participants' skills in working with classification algorithms in order to create a model capable of automatically classifying the group of animals in camera-trap photos. It tests their competence in data processing and in applying machine learning algorithms, as well as their ability to immerse themselves in the subject area and to apply computer vision algorithms in their solution.
The task helps to assess participants on their knowledge and skills in programming, zoology, image processing, machine learning and the application of technical solutions to real-world problems.
Task 2.4.1. Multi-class Classification of Animals in Camera-trap Photos (100 points)
Topics: programming, data exploration, machine learning, computer vision.
Problem statement
The task is devoted to classifying animals into broad groups. For this, participants receive access to unique data: images from camera traps provided by partner research organisations. Solving the task will reduce the workload on scientists associated with recognising species and, consequently, make population monitoring more efficient.
Why is this important?
Monitoring wild animal populations is an important task for the worldwide community of wildlife researchers. It helps to find out which animal species are endangered, how they behave in different periods of their lives, where they live, and much more.
Various tools are used to monitor animals, including camera traps: special cameras that are installed in the forest and react to movement in the frame. Every year these cameras deliver hundreds of thousands of photographs, in which the animals have to be found and categorised. This is very difficult and painstaking work, because among the species, whose total number can reach several hundred, there may be some that are visually hard to tell apart. In addition, only part of an animal may be in the frame at the moment the camera is triggered, and because many species are active at night, some photographs may be blurred or overexposed owing to the way the cameras work at night.
Data description
The dataset is a set of images and a file train.csv that maps each image to a particular group of animals: https://disk.yandex.ru/d/MiCI_OW7U1r_Dg/dataset.
The correspondence between the group index and its name is given below:
- 0 — hare,
- 1 — wild boar,
- 2 — cats,
- 3 — mustelids,
- 4 — bear,
- 5 — deer,
- 6 — panthers,
- 7 — bovids,
- 8 — canids,
- 9 — marmot.
Note that the dataset contains difficult examples: photos in which only a small part of an animal is in the frame, as well as night-time and blurred shots.
The labelling by group was carried out by research specialists engaged in monitoring the state of wildlife populations.
The data are split into a training set and a test set in a ratio of approximately 70% / 30%.
The test part is split into a public part and a private part in a ratio of approximately 40% / 60%.
Scoring criteria
This is a multi-class classification task, and the metric chosen was the macro F1 score (F1 is computed for each class and then averaged).
The following file contains a code fragment for computing the metric and evaluating participants' algorithms: https://disk.yandex.ru/d/MiCI_OW7U1r_Dg/ai-stage1.py.
Solution
You are required to develop an algorithm that classifies the group of animals in camera-trap photos and to present the result of its work as a CSV file with the columns image_name, predicted_class.
Link to the reference expert solution: https://disk.yandex.ru/d/MiCI_OW7U1r_Dg/baseline.ipynb.
Answer.
The solution to the task is a CSV file with predictions, uploaded to the competition platform to evaluate the quality of the solution.
Example of a submission file: https://disk.yandex.ru/d/MiCI_OW7U1r_Dg/sample_submission.csv.
Also, the solution that took the highest places on the private leaderboard: https://disk.yandex.ru/d/MiCI_OW7U1r_Dg/best_submission.csv.
Translated by SOTA. The Russian original is the official version and wins wherever the two differ. The statement is taken from pp. 99–101 of the 2024/25 task collection, which calls the baseline notebook the reference expert solution. In the data, the column unified_class holds the group names in Russian; the notebook glosses them. If you organise this olympiad and would like the translation removed, email [email protected] and we will take it down.
At a glance
- You get
- Images and
train.csv(image → group);baseline.ipynb; scoring codeai-stage1.py;sample_submission.csv. - You submit
- CSV with columns
image_nameandpredicted_class, uploaded to the competition platform. - Scoring
- Macro-averaged F1 score.
- Rules
- Individual task.
- Format
- Stage 1, engineering tour (100 points); in Stage 1 the mathematics, informatics and engineering tours are each worth 100 points and 50 points in total are needed to advance.