# Classification of Primitive Manufacturing Tasks from Filtered Event Data

arXiv: https://arxiv.org/abs/2303.09558 · HTML: https://mlsanity.com/paper/2303.09558/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 34 references that are in the map.
- First posted on arXiv 15 Mar 2023.

## Builds on (most cited first, 7 of 7)

- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [Temporal Binary Representation for Event-Based Action Recognition](https://mlsanity.com/paper/2010.08946/) (2020)
- [Learning Object-Action Relations from Bimanual Human Demonstration Using Graph Networks](https://mlsanity.com/paper/1908.08391/) (2019)
- [Event Camera Calibration of Per-pixel Biased Contrast Threshold](https://mlsanity.com/paper/2012.09378/) (2020)
- [Dynamic Vision Sensors for Human Activity Recognition](https://mlsanity.com/paper/1803.04667/) (2018)
- [A Proposed Set of Communicative Gestures for Human Robot Interaction and an RGB Image-based Gesture Recognizer Implemented in ROS](https://mlsanity.com/paper/2109.09908/) (2021)
- [Watch-n-Patch: Unsupervised Learning of Actions and Relations](https://mlsanity.com/paper/1603.03541/) (2016)

## Built on by (most cited first, 2 of 2)

- [DVS-PedX: Synthetic-and-Real Event-Based Pedestrian Dataset](https://mlsanity.com/paper/2509.04117/) (2025)
- [Event-based dataset for the detection and classification of manufacturing assembly tasks](https://mlsanity.com/paper/2405.14626/) (2024)

## Abstract (arXiv)

Collaborative robots are increasingly present in industry to support human activities. However, to make the human-robot collaborative process more effective, there are several challenges to be addressed. Collaborative robotic systems need to be aware of the human activities to (1) anticipate collaborative/assistive actions, (2) learn by demonstration, and (3) activate safety procedures in shared workspace. This study proposes an action classification system to recognize primitive assembly tasks from human motion events data captured by a Dynamic and Active-pixel Vision Sensor (DAVIS). Several filters are compared and combined to remove event data noise. Task patterns are classified from a continuous stream of event data using advanced deep learning and recurrent networks to classify spatial and temporal features. Experiments were conducted on a novel dataset, the dataset of manufacturing tasks (DMT22), featuring 5 classes of representative manufacturing primitives (PickUp, Place, Screw, Hold, Idle) from 5 participants. Results show that the proposed filters remove about 65% of all events (noise) per recording, conducting to a classification accuracy up to 99,37% for subjects that trained the system and 97.08% for new subjects. Data from a left-handed subject were successfully classified using only right-handed training data. These results are object independent.