Inst. Technische Informatik und Mikroelektronik

228 Items

Recent Submissions
An Integrated Approach to Visual Perception of Articulated Objects -- Data

Roberto, Martín-Martín ; Sebastian, Höfer ; Oliver, Brock (2016)

These are the rosbag files that accompany the ICRA2016 Paper "An Integrated Approach to Visual Perception of Articulated Objects". The rosbags contain RGBD recordings of moving articualted objects such as a drawer or a globe. Additionally there is ground truth information about the shapes of the objects supplied.

Coupled Recursive Estimation for Online Interactive Perception of Articulated Objects -- Online IP Data

Martin-Martin, Roberto (2019-05)

These are the rosbags used to evaluate the approach in "Coupled Recursive Estimation forOnline Interactive Perception of Articulated Objects", IJRR2019

A consensus-based elastic matching algorithm for mapping recall fixations onto encoding fixations in the looking-at-nothing paradigm

Wang, Xi ; Holmqvist, Kenneth ; Alexa, Marc (2021-03-22)

We present an algorithmic method for aligning recall fixations with encoding fixations, to be used in looking-at-nothing paradigms that either record recall eye movements during silence or want to speed up data analysis with recordings of recall data during speech. The algorithm utilizes a novel consensus-based elastic matching algorithm to estimate which encoding fixations correspond to later ...

3D reconstruction of anatomical structures from 2D X-ray images

Ehlke, Moritz (2021)

Two-dimensional (2D) radiographs are widely used for diagnosis, treatment planning, and follow-up in orthopedics. The images depict bone at high contrast to surrounding tissue and capture weight-bearing situations when taken in upright position. Compared to three-dimensional (3D) computed tomography (CT), 2D radiographs further expose the patient to relatively low radiation doses. Projectional ...

Computational discrimination between natural images based on gaze during mental imagery

Wang, Xi ; Ley, Andreas ; Koch, Sebastian ; Hays, James ; Holmqvist, Kenneth ; Alexa, Marc (2020-08-03)

When retrieving image from memory, humans usually move their eyes spontaneously as if the image were in front of them. Such eye movements correlate strongly with the spatial layout of the recalled image content and function as memory cues facilitating the retrieval procedure. However, how close the correlation is between imagery eye movements and the eye movements while looking at the original ...

Passive and Active Acoustic Sensing for Soft Pneumatic Actuators - Code and Data

Wall, Vincent ; Zöller, Gabriel ; Brock, Oliver (2020-12)

This data and code accompanies the paper "Passive and Active Acoustic Sensing for Soft Pneumatic Actuators" [1]. Abstract: We propose a sensorization method for soft pneumatic actuators that uses an embedded microphone and speaker to measure relevant actuator states. The physical state of the actuator influences the modulation of sound as it travels through the structure. Using simple machine ...

The RBO dataset of articulated objects and interactions

Martín-Martín, Roberto ; Eppner, Clemens ; Brock, Oliver (2019-08-01)

We present a dataset with models of 14 articulated objects commonly found in human environments and with RGB-D video sequences and wrenches recorded of human interactions with them. The 358 interaction sequences total 67 minutes of human manipulation under varying experimental conditions (type of interaction, lighting, perspective, and background). Each interaction with an object is annotated w...

Pixel2point: 3D object reconstruction from a single image using CNN and initial sphere

Afifi, Ahmed J. ; Magnusson, Jannes ; Soomro, Toufique A. ; Hellwich, Olaf (2020-12-23)

3D reconstruction from a single image has many useful applications. However, it is a challenging and ill-posed problem as various candidates can be a solution for the reconstruction. In this paper, we propose a simple, yet powerful, CNN model that generates a point cloud of an object from a single image. 3D data can be represented in different ways. Point clouds have proven to be a common and s...

Semantic-Fusion Gans for Semi-Supervised Satellite Image Classification

Roy, Subhankar ; Sangineto, Enver ; Demir, Begüm ; Sebe, Nicu (2018-09-06)

Most of the public satellite image datasets contain only a small number of annotated images. The lack of a sufficient quantity of labeled data for training is a bottleneck for the use of modern deep-learning based classification approaches in this domain. In this paper we propose a semi -supervised approach to deal with this problem. We use the discriminator (D) of a Generative Adversarial Netw...

A Progressive Content-Based Image Retrieval in JPEG 2000 Compressed Remote Sensing Archives

Preethy Byju, Akshara ; Demir, Begüm ; Bruzzone, Lorenzo (2020-02-24)

Due to the dramatically increased volume of remote sensing (RS) image archives, images are usually stored in a compressed format to reduce the storage size. Existing content-based RS image retrieval (CBIR) systems require as input fully decoded images, thus resulting in a computationally demanding task in the case of large-scale CBIR problems. To overcome this limitation, in this article, we pr...

A Quantitative Study of Locality in GPU Caches

Lal, Sohan ; Juurlink, Ben (2020-10-07)

Traditionally, GPUs only had programmer-managed caches. The advent of hardware-managed caches accelerated the use of GPUs for general-purpose computing. However, as GPU caches are shared by thousands of threads, they are usually a victim of contention and can suffer from thrashing and high miss rate, in particular, for memory-divergent workloads. As data locality is crucial for performance, the...

QSLC: Quantization-Based, Low-Error Selective Approximation for GPUs

Lal, Sohan ; Lucas, Jan ; Juurlink, Ben (2020)

GPUs use a large memory access granularity (MAG) that often results in a low effective compression ratio for memory compression techniques. The low effective compression ratio is caused by a significant fraction of compressed blocks that have a few bytes above a multiple of MAG. While MAG-aware selective approximation, based on a tree structure, has been used to increase the effective compressi...

Efficient utilization of vector extensions in microprocessors

Pohl, Angela (2020)

Since the early 1990s, microprocessors have been enhanced with vector extensions to exploit data-level parallelism in applications. Programs are sped up by applying the same instruction to multiple data elements, grouped in a vector, in parallel. Up to this day, efficient utilization of such vector extensions remains challenging, however. While manually transforming code to exploit vector regis...

High-Rankness Regularized Semi-Supervised Deep Metric Learning for Remote Sensing Imagery

Kang, Jian ; Fernández-Beltrán, Rubén ; Ye, Zhen ; Tong, Xiaohua ; Ghamisi, Pedram ; Plaza, Antonio (2020-08-12)

Deep metric learning has recently received special attention in the field of remote sensing (RS) scene characterization, owing to its prominent capabilities for modeling distances among RS images based on their semantic information. Most of the existing deep metric learning methods exploit pairwise and triplet losses to learn the feature embeddings with the preservation of semantic-similarity, ...

High-throughput HEVC CABAC decoding

Habermann, Philipp (2020)

Video applications have emerged in various fields of our everyday life. They have continuously enhanced the user experience in entertainment and communication services. All this would not have been possible without the evolution of video compression standards and computer architectures over the last decades. Modern video codecs employ sophisticated algorithms to transform raw video data to an i...

Robust Fine Registration of Multisensor Remote Sensing Images Based on Enhanced Subpixel Phase Correlation

Ye, Zhen ; Kang, Jian ; Yao, Jing ; Song, Wenping ; Liu, Sicong ; Luo, Xin ; Xu, Yusheng ; Tong, Xiaohua (2020-08-04)

Automatic fine registration of multisensor images plays an essential role in many remote sensing applications. However, it is always a challenging task due to significant radiometric and textural differences. In this paper, an enhanced subpixel phase correlation method is proposed, which embeds phase congruency-based structural representation, L1-norm-based rank-one matrix approximation with ad...

Analyzing and improving image-based 3D surface reconstruction challenged by weak texture or low illumination

Aldeeb, Nader H. (2020)

Image-based 3D reconstruction is a photogrammetric technique that recovers the real 3D world from its 2D images. It has become an active research field in computer vision because of its application in numerous areas, including science, medicine, culture, military, architecture, and entertainment. The principle that stands behind image-based 3D reconstruction is called triangulation. It is used...

An Approach To Super-Resolution Of Sentinel-2 Images Based On Generative Adversarial Networks

Zhang, Kexin ; Sumbul, Gencer ; Demir, Begüm (2020-06-02)

This paper presents a generative adversarial network based super-resolution (SR) approach (which is called as S2GAN) to enhance the spatial resolution of Sentinel-2 spectral bands. The proposed approach consists of two main steps. The first step aims to increase the spatial resolution of the bands with 20m and 60m spatial resolutions by the scaling factors of 2 and 6, respectively. To this end,...

Unsupervised Remote Sensing Image Retrieval Using Probabilistic Latent Semantic Hashing

Fernandez-Beltran, Ruben ; Demir, Begüm ; Pla, Filiberto ; Plaza, Antonio (2020-02-06)

Unsupervised hashing methods have attracted considerable attention in large-scale remote sensing (RS) image retrieval, due to their capability for massive data processing with significantly reduced storage and computation. Although existing unsupervised hashing methods are suitable for operational applications, they exhibit limitations when accurately modeling the complex semantic content prese...

SD-RSIC: Summarization-Driven Deep Remote Sensing Image Captioning

Sumbul, Gencer ; Nayak, Sonali ; Demir, Begüm (2020-10-26)

Deep neural networks (DNNs) have been recently found popular for image captioning problems in remote sensing (RS). Existing DNN-based approaches rely on the availability of a training set made up of a high number of RS images with their captions. However, captions of training images may contain redundant information (they can be repetitive or semantically similar to each other), resulting in in...