Muhamad Risqi Utama Saputra

Muhamad Risqi Utama Saputra
University of Oxford | OX · Department of Computer Science

M.Eng.

About

31
Publications
13,561
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
686
Citations

Publications

Publications (31)
Article
In the last few decades, Structure from Motion (SfM) and visual Simultaneous Localization and Mapping (visual SLAM) techniques have gained significant interest from both the computer vision and robotic communities. Many variants of these techniques have started to make an impact in a wide range of applications, including robot navigation and augmen...
Preprint
In the last decade, supervised deep learning approaches have been extensively employed in visual odometry (VO) applications, which is not feasible in environments where labelled data is not abundant. On the other hand, unsupervised deep learning approaches for localization and mapping in unknown environments from unlabelled data have received compa...
Conference Paper
Full-text available
Inspired by the cognitive process of humans and animals, Curriculum Learning (CL) trains a model by gradually increasing the difficulty of the training data. In this paper, we study whether CL can be applied to complex geometry problems like estimating monocular Visual Odometry (VO). Unlike existing CL approaches, we present a novel CL strategy for...
Conference Paper
Full-text available
This paper presents a novel method to distill knowledge from a deep pose regressor network for efficient Visual Odometry (VO). Standard distillation relies on "dark knowledge" for successful knowledge transfer. As this knowledge is not available in pose regression and the teacher prediction is not always accurate, we propose to emphasize the knowle...
Preprint
Visual odometry shows excellent performance in a wide range of environments. However, in visually-denied scenarios (e.g. heavy smoke or darkness), pose estimates degrade or even fail. Thermal imaging cameras are commonly used for perception and inspection when the environment has low visibility. However, their use in odometry estimation is hampered...
Preprint
Full-text available
This paper presents a multimodal indoor odometry dataset, OdomBeyondVision, featuring multiple sensors across the different spectrum and collected with different mobile platforms. Not only does OdomBeyondVision contain the traditional navigation sensors, sensors such as IMUs, mechanical LiDAR, RGBD camera, it also includes several emerging sensors...
Article
In the last decade, numerous supervised deep learning approaches have been proposed for visual inertial odometry (VIO) and depth map estimation, which require large amounts of labelled data. To overcome the data limitation, self-supervised learning has emerged as a promising alternative that exploits constraints such as geometric and photometric co...
Preprint
Full-text available
Ubiquitous positioning for pedestrian in adverse environment has served a long standing challenge. Despite dramatic progress made by Deep Learning, multi-sensor deep odometry systems yet pose a high computational cost and suffer from cumulative drifting errors over time. Thanks to the increasing computational power of edge devices, we propose a nov...
Preprint
Full-text available
Camera localization is a fundamental and crucial problem for many robotic applications. In recent years, using deep-learning for camera-based localization has become a popular research direction. However, they lack robustness to large domain shifts, which can be caused by seasonal or illumination changes between training and testing data sets. Data...
Article
Simultaneous localization and mapping (SLAM) system typically employs vision-based sensors to observe the surrounding environment. However, the performance of such systems highly depends on the ambient illumination conditions. In scenarios with adverse visibility or in the presence of airborne particulates (e.g., smoke, dust, etc.), alternative mod...
Article
Recent learning-based approaches have achieved impressive results in the field of single-shot camera localization. However, how best to fuse multiple modalities (e.g., image and depth) and to deal with degraded or missing input are less well studied. In particular, we note that previous approaches towards deep fusion do not perform significantly be...
Preprint
Full-text available
Simultaneous Localization and Mapping (SLAM) system typically employ vision-based sensors to observe the surrounding environment. However, the performance of such systems highly depends on the ambient illumination conditions. In scenarios with adverse visibility or in the presence of airborne particulates (e.g. smoke, dust, etc.), alternative modal...
Preprint
Full-text available
Positional estimation is of great importance in the public safety sector. Emergency responders such as fire fighters, medical rescue teams, and the police will all benefit from a resilient positioning system to deliver safe and effective emergency services. Unfortunately, satellite navigation (e.g., GPS) offers limited coverage in indoor environmen...
Preprint
Robust and accurate trajectory estimation of mobile agents such as people and robots is a key requirement for providing spatial awareness to emerging capabilities such as augmented reality or autonomous interaction. Although currently dominated by vision based techniques e.g., visual-inertial odometry, these suffer from challenges with scene illumi...
Article
Visual odometry shows excellent performance in a wide range of environments. However, in visually-denied scenarios (e.g. heavy smoke or darkness), pose estimates degrade or even fail. Thermal cameras are commonly used for perception and inspection when the environment has low visibility. However, their use in odometry estimation is hampered by the...
Preprint
In the last decade, numerous supervised deep learning approaches requiring large amounts of labeled data have been proposed for visual-inertial odometry (VIO) and depth map estimation. To overcome the data limitation, self-supervised learning has emerged as a promising alternative, exploiting constraints such as geometric and photometric consistenc...
Preprint
Odometry is of key importance for localization in the absence of a map. There is considerable work in the area of visual odometry (VO), and recent advances in deep learning have brought novel approaches to VO, which directly learn salient features from raw images. These learning-based approaches have led to more accurate and robust VO systems. Howe...
Article
Full-text available
Considered as an effective learning strategy for dyslexia, multisensory approach demands visual, auditory, and kinesthetic activity. While development of software application implementing multisensory approach has shown promising result, previous applications did not accurately resemble multisensory strategy because there are no kinesthetic impleme...
Article
Considered as an effective learning strategy for dyslexia, multisensory approach demands visual, auditory, and kinesthetic activity. While development of software application implementing multisensory approach has shown promising result, previous applications did not accurately resemble multisensory strategy because there are no kinesthetic impleme...
Article
Full-text available
As a specific learning disability, dyslexia is not curable, yet manageable. Dyslexia management is usually conducted as extra learning program using multisensory method which is called remediation. However, some studies indicate that students with dyslexia have lower motivation in learning than students without dyslexia. This research design a lear...
Conference Paper
Full-text available
Penelitian ini mengembangkan aplikasi LexiPal sebagai aplikasi belajar membaca permulaan untuk anak-anak disleksia. Aplikasi LexiPal dikembangkan berdasarkan pendekatan multisensori sehingga melibatkan sebanyak mungkin indera anak seperti visual, auditori, taktil, dan kinestetik. LexiPal juga menyediakan aplikasi yang lebih komprehensif dengan mema...
Conference Paper
Full-text available
This paper describes “learn-to-read” application for assisting therapist/teacher in conducting remediation programme of dyslexic children. The application is developed in Indonesian language for 5-7 years old dyslexic. Based on multisensory approach, the application is designed to utilize all of sensory receptors of dyslexic hence incorporating vis...
Conference Paper
Full-text available
Abstract—Visually impaired people need assistance to navigate safely, especially in indoor environment. This research developed an obstacle avoidance system for visually impaired using Kinect’s depth camera as the main vision device. A new approach called auto-adaptive thresholding is proposed to detect and to calculate the distance of obstacle fro...
Conference Paper
Full-text available
This research developed an application that could tracks and locates human’s presence and position in indoor environment using multiple depth-cameras. Kinect as the most affordable device that equipped with depth- camera was used in this work. The application obtains stream data from Kinect and analyzes presence of human using skeletal tracking lib...
Article
This research developed an application that could tracks and locates human's presence and position in indoor environment using multiple depth-cameras. Kinect as the most affordable device that equipped with depth-camera was used in this work. The application obtains stream data from Kinect and analyzes presence of human using skeletal tracking libr...

Network

Cited By