no code implementations • 22 Mar 2024 • Nicolas Baumann, Michael Baumgartner, Edoardo Ghignone, Jonas Kühne, Tobias Fischer, Yung-Hsu Yang, Marc Pollefeys, Michele Magno
Accurate detection and tracking of surrounding objects is essential to enable self-driving vehicles.
no code implementations • 18 Mar 2024 • Jakub Mandula, Jonas Kühne, Luca Pascarella, Michele Magno
Unmanned Aerial Vehicles (UAVs) are gaining popularity in civil and military applications.
1 code implementation • 8 Feb 2024 • Haotong Qin, Xudong Ma, Xingyu Zheng, Xiaoyang Li, Yang Zhang, Shouda Liu, Jie Luo, Xianglong Liu, Michele Magno
This paper proposes a novel IR-QLoRA for pushing quantized LLMs with LoRA to be highly accurate through information retention.
1 code implementation • 6 Feb 2024 • Wei Huang, Yangdong Liu, Haotong Qin, Ying Li, Shiming Zhang, Xianglong Liu, Michele Magno, Xiaojuan Qi
Pretrained large language models (LLMs) exhibit exceptional general language processing capabilities but come with significant demands on memory and computational resources.
no code implementations • 11 Jan 2024 • Sizhen Bian, Mengxi Liu, Bo Zhou, Paul Lukowicz, Michele Magno
To this end, we first sorted the explorations into three domains according to the involved body forms: body-part electric field, whole-body electric field, and body-to-body electric field, and enumerated the state-of-art works in the domains with a detailed survey of the backed sensing tricks and targeted applications.
1 code implementation • 21 Dec 2023 • Tobias Margiani, Silvano Cortesi, Milena Keller, Christian Vogt, Tommaso Polonelli, Michele Magno
Accurate and low-power indoor localization is becoming more and more of a necessity to empower novel consumer and industrial applications.
no code implementations • 15 Dec 2023 • Pietro Bonazzi, Yawei Li, Sizhen Bian, Michele Magno
We present "Q-Segment", a quantized real-time segmentation algorithm, and conduct a comprehensive evaluation on a low-power edge vision platform with an in-sensors processor, the Sony IMX500.
1 code implementation • 1 Dec 2023 • Pietro Bonazzi, Sizhen Bian, Giovanni Lippolis, Yawei Li, Sadique Sheik, Michele Magno
This paper introduces a neuromorphic methodology for eye tracking, harnessing pure event data captured by a Dynamic Vision Sensor (DVS) camera.
Ranked #1 on Pupil Detection on INI-30
no code implementations • 24 Nov 2023 • Jonah Imfeld, Silvano Cortesi, Philipp Mayer, Michele Magno
Spatial and contextual awareness has the potential to revolutionize sensor nodes, enabling spatially augmented data collection and location-based services.
no code implementations • 13 Nov 2023 • Liam Boyle, Nicolas Baumann, Seonyeong Heo, Michele Magno
Advances in lightweight neural networks have revolutionized computer vision in a broad range of IoT applications, encompassing remote monitoring and process automation.
no code implementations • 3 Nov 2023 • Julian Moosmann, Jakub Mandula, Philipp Mayer, Luca Benini, Michele Magno
This work quantitatively evaluates a multi-modal camera setup for fusing high-resolution DVS data with RGB image data by static camera alignment.
no code implementations • 2 Nov 2023 • Julian Moosmann, Pietro Bonazzi, Yawei Li, Sizhen Bian, Philipp Mayer, Luca Benini, Michele Magno
To this goal, we designed a smart glasses prototype as a research platform featuring two microcontrollers, including a novel milliwatt-power RISC-V parallel processor with a hardware accelerator for visual AI, and a Bluetooth low-power module for communication.
Ranked #1 on Object Detection on PASCAL VOC
1 code implementation • 31 Oct 2023 • Marco Giordano, Silvano Cortesi, Prodromos-Vasileios Mekikis, Michele Crabolu, Giovanni Bellusci, Michele Magno
In the ever-growing Internet of Things (IoT) landscape, smart power management algorithms combined with energy harvesting solutions are crucial to obtain self-sustainability.
no code implementations • 23 Oct 2023 • Marco Giordano, Silvano Cortesi, Michele Crabolu, Lavinia Pedrollo, Giovanni Bellusci, Tommaso Bendinelli, Engin Türetken, Andrea Dunbar, Michele Magno
Known for its accuracy, scalability, and fast training for time-series classification, in this paper, it is proposed as a TinyML algorithm for inference on resource-constrained IoT devices.
no code implementations • 23 Oct 2023 • Silvano Cortesi, Marc Dreher, Michele Magno
Experimental evaluation with the real-time data processing has been evaluated and presented in a 7. 2 m by 7. 2 m room with furniture and 5 beacon nodes.
no code implementations • 25 Sep 2023 • Lukas Schulthess, Thorir Mar Ingolfsson, Marc Nölke, Michele Magno, Luca Benini, Christoph Leitner
In particular, a fine-grained control of the center of gravity in the in-run is essential.
no code implementations • 15 Sep 2023 • Steven Marty, Federico Pantanella, Andrea Ronco, Kanika Dheman, Michele Magno
At the same distance, the 60 GHz and the 120 GHz radar system shows the least noise level, 0. 0lmm at 0{\deg} angle of incidence, and error in range estimation 0. 64 +- 0. 01 cm and 0. 04 +- 0. 0 cm respectively.
no code implementations • 5 Sep 2023 • Philipp Schilk, Niccolò Polvani, Andrea Ronco, Milos Cernak, Michele Magno
Such microphones can record the wearer's speech with much greater isolation, enabling personalized voice activity detection and further audio enhancement applications.
1 code implementation • 1 Aug 2023 • Sizhen Bian, Michele Magno
Energy efficiency and low latency are crucial requirements for designing wearable AI-empowered human activity recognition systems, due to the hard constraints of battery operations and closed-loop feedback.
2 code implementations • 15 Jul 2023 • Pietro Bonazzi, Thomas Ruegg, Sizhen Bian, Yawei Li, Michele Magno
We propose TinyTracker, a highly efficient, fully quantized model for 2D gaze estimation designed to maximize the performance of the edge vision systems considered in this study.
Ranked #2 on Gaze Estimation on GazeCapture
no code implementations • 12 Jul 2023 • Julian Moosmann, Hanna Mueller, Nicky Zimmerman, Georg Rutishauser, Luca Benini, Michele Magno
With this paper, we demonstrate the suitability and flexibility of TinyissimoYOLO on state-of-the-art detection datasets for real-time ultra-low-power edge inference.
no code implementations • 27 May 2023 • Sizhen Bian, Lukas Schulthess, Georg Rutishauser, Alfio Di Mauro, Luca Benini, Michele Magno
The interest in dynamic vision sensor (DVS)-powered unmanned aerial vehicles (UAV) is raising, especially due to the microsecond-level reaction time of the bio-inspired event sensor, which increases robustness and reduces latency of the perception tasks compared to a RGB camera.
no code implementations • 27 May 2023 • Sizhen Bian, Alexander Rupp, Michele Magno
The system we have implemented is a working prototype of a bigger end goal and is supposed to initialize progress toward a smarter, more efficient, and still privacy-respect gym environment in the future.
no code implementations • 22 May 2023 • Jonas Kühne, Michele Magno, Luca Benini
The paper characterizes the optical flow sensor in high frame-rate, low-latency settings, with a frame rate of up to 88 fps at the full resolution of 1124 by 1364 pixels and up to 240 fps at a reduced camera resolution of 280 by 336, for both classical camera images and optical flow data.
no code implementations • 22 May 2023 • Jonas Kühne, Michele Magno, Luca Benini
On micro and nano UAVs, real-time calculation of the optical flow is run on low power and resource-constrained microcontroller units (MCUs).
no code implementations • 22 May 2023 • Julian Moosmann, Marco Giordano, Christian Vogt, Michele Magno
The proposed quantized network architecture with 422k parameters, enables real-time object detection on embedded microcontrollers, and it has been evaluated to exploit CNN accelerators.
no code implementations • 24 Mar 2023 • Kanika Dheman, Stefan Walser, Philipp Mayer, Manuel Eggimann, Marko Kozomara, Denise Franke, Thomas Hermanns, Hugo Sax, Simone Schürle, Michele Magno
Here, a deep learning-based algorithm is presented that processes the local BI of the lower abdomen and suppresses artefacts to measure the bladder volume quantitatively, non-invasively and without the continuous need for additional personnel.
no code implementations • 13 Jan 2023 • Sizhen Bian, Xiaying Wang, Tommaso Polonelli, Michele Magno
We also introduced an open data set composed of fifty sessions of eleven gym workouts collected from ten subjects that is publicly available.
no code implementations • 9 Dec 2022 • Philipp Mayer, Michele Magno, Luca Benini
The energy consumption for position updates, with an accuracy of $40~cm$ (2D) in realistic non-line-of-sight conditions, is $10. 84~mJ$.
no code implementations • 1 Dec 2022 • Hanna Poikonen, Tomasz Zaluska, Xiaying Wang, Michele Magno, Manu Kapur
Our results clarify the different neural signature, analyzed by HFD, of math experts and novices during complex math and suggest machine learning as a promising data-driven approach to understand the brain processes in expertise and mathematical cognition.
1 code implementation • 25 Nov 2022 • Hanna Müller, Nicky Zimmerman, Tommaso Polonelli, Michele Magno, Jens Behley, Cyrill Stachniss, Luca Benini
Experimental evaluation using a nano-UAV open platform demonstrated that the proposed solution is capable of localizing on a 31. 2m$\boldsymbol{^2}$ map with 0. 15m accuracy and an above 95% success rate.
no code implementations • 24 May 2022 • Tommaso Polonelli, Hanna Müller, Weikang Kong, Raphael Fischer, Luca Benini, Michele Magno
This paper presents a low-power, self-sustainable, and modular wireless sensor node for aerodynamic and acoustic measurements on wind turbines and other industrial structures.
no code implementations • 28 Mar 2022 • Xiaying Wang, Michael Hersche, Michele Magno, Luca Benini
A brain--machine interface (BMI) based on motor imagery (MI) enables the control of devices using brain signals while the subject imagines performing a movement.
no code implementations • 12 Jan 2021 • Gianmarco Cerutti, Renzo Andri, Lukas Cavigelli, Michele Magno, Elisabetta Farella, Luca Benini
This BNN reaches a 77. 9% accuracy, just 7% lower than the full-precision version, with 58 kB (7. 2 times less) for the weights and 262 kB (2. 4 times less) memory in total.
1 code implementation • 25 Jun 2020 • Moritz Scherer, Michele Magno, Jonas Erb, Philipp Mayer, Manuel Eggimann, Luca Benini
Furthermore, the gesture recognition classifier has been implemented on a Parallel Ultra-Low Power Processor, demonstrating that real-time prediction is feasible with only 21 mW of power consumption for the full TCN sequence prediction network, while a system-level power consumption of less than 100 mW is achieved.
no code implementations • 31 Mar 2020 • Xiaying Wang, Michael Hersche, Batuhan Tömekce, Burak Kaya, Michele Magno, Luca Benini
Our novel method further scales down the standard EEGNet at a negligible accuracy loss of 0. 31% with 7. 6x memory footprint reduction and a small accuracy loss of 2. 51% with 15x reduction.
no code implementations • 28 Feb 2020 • Michele Magno, Xiaying Wang, Manuel Eggimann, Lukas Cavigelli, Luca Benini
This work presents InfiniWolf, a novel multi-sensor smartwatch that can achieve self-sustainability exploiting thermal and solar energy harvesting, performing computationally high demanding tasks.
no code implementations • 10 Dec 2019 • Xiaying Wang, Lukas Cavigelli, Manuel Eggimann, Michele Magno, Luca Benini
Synthetic aperture radar (SAR) data is becoming increasingly available to a wide range of users through commercial service providers with resolutions reaching 0. 5m/px.
1 code implementation • 8 Nov 2019 • Xiaying Wang, Michele Magno, Lukas Cavigelli, Luca Benini
The growing number of low-power smart devices in the Internet of Things is coupled with the concept of "Edge Computing", that is moving some of the intelligence, especially machine learning, towards the edge of the network.
no code implementations • 9 Nov 2016 • Lukas Cavigelli, Dominic Bernath, Michele Magno, Luca Benini
The required communication links and archiving of the video data are still expensive and this setup excludes preemptive actions to respond to imminent threats.