- Medical Imaging Techniques and Applications
- Neural Networks and Applications
- Advanced Vision and Imaging
- Control Systems and Identification
- Rough Sets and Fuzzy Logic
- Robotics and Sensor-Based Localization
- Fuzzy Systems and Optimization
- Image and Object Detection Techniques
- Image and Signal Denoising Methods
- Advanced MRI Techniques and Applications
- Medical Image Segmentation Techniques
- Multi-Criteria Decision Making
- Fuzzy Logic and Control Systems
- Image Retrieval and Classification Techniques
- Radiation Detection and Scintillator Technologies
- Advanced Steganography and Watermarking Techniques
- Digital Media Forensic Detection
- Advanced X-ray and CT Imaging
- Bayesian Modeling and Causal Inference
- Image Processing Techniques and Applications
- Optical measurement and interference techniques
- Advanced Image and Video Retrieval Techniques
- Advanced Image Processing Techniques
- QR Code Applications and Technologies
- Probabilistic and Robust Engineering Design
Laboratoire d'Informatique, de Robotique et de Microélectronique de Montpellier
2015-2024
Université de Montpellier
2015-2024
Centre National de la Recherche Scientifique
2014-2023
Centre Hospitalier Universitaire de Montpellier
2020
University of Zurich
2019
Since several years, the protection of multimedia data is becoming very important. The this can be done with encryption or hiding algorithms. To decrease transmission time, compression necessary. few a new problem trying to combine in single step, compression, and hiding. So far, solutions have been proposed image for example. Nowadays, challenge consists embed encrypted images. entropy maximal, embedding considered like noise, not possible by using standard A idea apply reversible...
The quick response (QR) code was designed for storage information and high-speed reading applications. In this paper, we present a new rich QR that has two levels can be used document authentication. This code, named two-level public private levels. level is the same as standard level; therefore, it readable by any classical application. constructed replacing black modules specific textured patterns. It consists of encoded using q-ary with an error correction capacity. allows us not only to...
In maize, silks are hundreds of filaments that simultaneously emerge from the ear for collecting pollen over a period 1–7 days, which largely determines grain number especially under water deficit. Silk growth is major trait drought tolerance in but its phenotyping difficult at throughputs needed genetic analyses. We have developed reproducible pipeline follows and silk growths every day plants, based on an detection algorithm drives robotized camera obtaining detailed images ears silks....
This paper proposes a new calibration method for perception system designed mobile robot. The we use is made of gray-level CCD camera and laser rangefinder. problem to match data provided by those two sensors therefore identify the rangefinder/camera transformation. A process based upon specific pattern used such Adapted procedures define geometric relationship between these sensors. We have tested in simulation several models order most efficient one has been chosen implemented on an...
This paper proposes a tentative and original survey of meeting points between Knowledge Representation Reasoning (KRR) Machine Learning (ML), two areas which have been developed quite separately in the last four decades. First, some common concerns are identified discussed such as types representation used, roles knowledge data, lack or excess information, need for explanations causal understanding. Then, is organised seven sections covering most territory where KRR ML meet. We start with...
A classic approach to obtain High Dynamic Range Images (HDRI) consists in combining multiple images of the same scene with varying exposures. However, if is not static during time capture, moving objects will appear blurry and ghosted, i.e. locations. Detecting removing ghosting artifacts an important issue for automatic generation HDRI dynamic scenes. This paper first describes a new method detecting regions where occur based on order relation between pixel values consecutive images....
Our study aims to provide a comparison of the P- and L-band TomoSAR profiles, Land Vegetation Ice Sensor (LVIS), discrete return LiDAR assess ability for monitor estimate tropical forest structure parameters enhanced management support biomass missions. The relies on unique UAVSAR Jet propulsion Laboratory (JPL)/NASA data, P-band data acquired by ONERA airborne system (SETHI), Small Footprint (SFL), NASA Land, (LVIS) datasets in 2015 2016 frame AfriSAR campaign. Prior multi-baseline...
The number of precaudal vertebrae in all extant crocodylians is remarkably conservative, with nine cervicals, 15 dorsals and two sacrals, a pattern present also their closest extinct relatives. consistent vertebral count indicates tight control axial patterning by Hox genes during development. Here we report on deviation from this based an associated skeleton the giant caimanine Purussaurus, member crown Crocodylia, several other specimens Neogene northern neotropics. P. mirandai first...
The availability of high quality copy machines provides a large amount printed document counterfeits. Numerous authentication techniques based on security printing, graphical codes, hashing or local have been suggested earlier. In this paper, we propose novel system sensitivity new two level QR (2LQR) code to copying process. This 2LQR contains specific textured patterns, which are sensitive printing and processes. Therefore, it can be used detect unauthorized duplication. Experimental...
We address the problem of autonomous exploration unknown environments using a Micro Aerial Vehicle (MAV) equipped with an active depth sensor. As such, task consists in mapping gradually discovered environment while planning envisioned trajectories real-time, on-board computation only. To do so, we present SplatPlanner, end-to-end planner that is based on novel Permutohedral Frontier Filtering (PFF) which relies combination highly efficient operations stemming from bilateral filtering...