Video Analysis

Audio and Visual Content Analysis

Image and video analysis with a focus on facial analysis

In the field of video analysis, we develop solutions for customer-specific problems in the areas of media, security and biodiversity that are not covered by standard solutions.

To answer specific questions from research and development, we combine established procedures and methods of machine learning and image analysis. They are recombined depending on the application and individually trained and optimized as required.

This includes the customized development and integration of software solutions for facial analysis, the use-case-specific training of models and their deployment as well as the evaluation and benchmarking of methods and solutions relating to facial analysis and machine learning.

News and upcoming events

 

Event

Workshop Digital Broadcasting

The next Workshop Digital Broadcasting will take place in fall 2024.

 

Pressemitteilung / 21.11.2023

MaLisa Study 2023

Study on climate change in German television programming: Fraunhofer IDMT analyzes 20 TV channels

 

Pressemitteilung / 11.9.2023

Audiovisual Identity Suite

Novelty at the fair: Fraunhofer IDMT showcases new tool for simultaneous face and speaker recognition at IBC 2023

Facial analysis as an application of computer vision

Computer vision is shaping and driving research and development in the fields of machine learning and artificial intelligence. Especially Facial analysis in plays a central role here.

The face is the most important external characteristic of a person and consists of a unique combination of individual features. These features are not only used to distinguish known from unknown people. They also help to assess a person's age or emotional state, for example.

Facial analysis is a branch of image and video analysis in the field of computer vision, which deals with the computer-assisted processing and analysis of camera images. It involves the automatic extraction of a wide range of information from image and video recordings of faces. This procedure enables the extraction of features that can be used to detect or recognize people, but also to differentiate between people by age or perceived gender, for example.

Efficient processing of video data and scientific evaluation of methods

The amount of data generated by camera recordings is extremely large compared to other sensor data, especially when it comes to video recordings.. This results in challenges for the entire processing chain, which are reflected in the complexity of the networks used, the size of the models and the computing power required, among other things. Compared to the processing of individual images, these requirements increase even more dramatically when analyzing videos (moving images).

This results in various challenges and questions:

  • How can methods and processes be transferred from still images to moving images?
  • How can existing facial models and analysis processes be further optimized?
  • How can the AI/ML models be scientifically evaluated and corrected in order to avoid unintended bias in the results?
  • How can the accuracy of perceived gender and age classifications be further improved?
  • How can analysis processes also be implemented on small devices (SoC)?

In addition to the technical challenges, especially facial analysis also raises questions about social acceptance (privacy and data protection) as well as fairness and trustworthiness (bias).

 

Research project

SAISBECO

Biodiversity identification software to automatically search through single images, video and audio recordings for sequences involving great apes. 

 

Research project

iMediaCities

Development of a digital platform to make the audio-visual cultural heritage of European cities accessible

 

Research project

SPADE

Intelligent ecosystem for the development of drones and unmanned aerial objects

 

White paper

ConstructionsAIt

Multimodal AI-based technologies for automatic construction site monitoring

 

Research project

Media analysis

Study on climate change in German television programming: Fraunhofer IDMT analyzes 20 TV channels

Produkte

 

Facial Analysis Technologies

AI-Based Facial Recognition and Analysis

 

MaskCognizer

AI-based face mask detection for public health and safety based on a Jetson nano 

 

IDCheck

AI-based identity verification

 

Audiovisual Identity Suite

Combined audio and video analysis for automatic annotation of large amounts of A/V content.

Services

  • Visual AI Assessment: Combined audio and video analysis for automatic annotation of large amounts of A/V content

Jahr
Year
Titel/Autor:in
Title/Author
Publikationstyp
Publication Type
2023 Comparison of Object Detection Algorithms for Livestock Monitoring of Sheep in UAV images
Doll, Oliver; Loos, Alexander
Vortrag
Presentation
2022 Construction-sAIt: Multi-modal AI-driven technologies for construction site monitoring
Abeßer, Jakob; Loos, Alexander; Sharma, Prachi
Konferenzbeitrag
Conference Paper
2022 Web-based Auralization of Noise Protection Measures in Urban Living Spaces
Fiedler, Bernhard; Millitzer, Jonathan; Weigel, Christian; Mees, Valentin; Loos, Alexander; Lorenz, Wolfgang; Sladeczek, Christoph; Bös, Joachim
Konferenzbeitrag
Conference Paper
2018 I-Media-Cities: Automatic Metadata Enrichment of Historic Media Content
Loos, Alexander; Weigel, Christian
Konferenzbeitrag
Conference Paper
2018 Towards Automatic Detection of Animals in Camera-Trap Images
Loos, Alexander; Koehler, Mona; Weigel, Christian
Konferenzbeitrag
Conference Paper
2017 Automated face detection for occurrence and occupancy estimation in chimpanzees
Crunchant, A.-S.; Egerer, M.; Loos, A.; Burghardt, T.; Zuberbühler, K.; Corogenes, K.; Leinert, V.; Kulik, L.; Kühl, H.S.
Zeitschriftenaufsatz
Journal Article
2016 Chimpanzee faces in the wild: Log-euclidean CNNs for predicting identities and attributes of primates
Freytag, A.; Rodner, E.; Simon, M.; Kühl, H.S.; Denzler, J.; Loos, A.
Konferenzbeitrag
Conference Paper
2015 Face recognition for great apes: Identification of primates in videos
Loos, Alexander; Kalyanasundaram, Talat Anand Mohan
Konferenzbeitrag
Conference Paper
2013 Chimpanzee identification using global and local features
Loos, Alexander
Konferenzbeitrag
Conference Paper
2013 Synthesising unseen image conditions to enhance classification accuracy for sparse datasets: Applied to chimpanzee face recognition
Sandwell, Roz; Loos, Alexander; Burghardt, Tilo
Konferenzbeitrag
Conference Paper
2013 An automated chimpanzee identification system using face detection and recognition
Loos, Alexander; Ernst, Andreas
Zeitschriftenaufsatz
Journal Article
2012 Identification of Great Apes using Gabor features and Locality Preserving Projections
Loos, Alexander
Konferenzbeitrag
Conference Paper
2011 Facial recognition for primate photo identification
Loos, Alexander; Pfitzer, Martin; Aporius, Laura
Konferenzbeitrag
Conference Paper
2011 Identification of great apes using face recognition
Loos, Alexander; Pfitzer, Martin; Aporius, Laura
Konferenzbeitrag
Conference Paper
2011 Automated detection of errors and quality issues in audio-visual content
Kühhirt, U.; Paduschek, R.; Nowak, S.
Konferenzbeitrag
Conference Paper
2010 SAISBECO - a semi-automated audiovisual species and individual identification system for behavioral ecological research and conservation
Loos, Alexander; Kühl, Hjalmar
Konferenzbeitrag
Conference Paper
Diese Liste ist ein Auszug aus der Publikationsplattform Fraunhofer-Publica

This list has been generated from the publication platform Fraunhofer-Publica