The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over the last few years, bringing the accuracy of automated segmentation close to human performance. However, these models have been all too often trained and validated using cardiac imaging samples from single clinical centres or homogeneous imaging protocols. This has prevented the development and validation of models that are generalizable across different clinical centres, imaging conditions or scanner vendors. To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference. A total of 14 teams submitted different solutions to the problem, combining various baseline models, data augmentation strategies, and domain adaptation techniques. The obtained results indicate the importance of intensity-driven data augmentation, as well as the need for further research to improve generalizability towards unseen scanner vendors or new imaging protocols. Furthermore, we present a new resource of 375 heterogeneous CMR datasets acquired by using four different scanner vendors in six hospitals and three different countries (Spain, Canada and Germany), which we provide as open-access for the community to enable future research in the field.

We present a methodology to recover the geometrical calibration of conventional X-ray settings with the help of an ordinary video camera and visible fiducials that are present in the scene. After calibration, equivalent points of interest can be easily identifiable with the help of the epipolar geometry. The same procedure also allows the measurement of real anatomic lengths and angles and obtains accurate 3D locations from image points. Our approach completely eliminates the need for X-ray-opaque reference marks (and necessary supporting frames) which can sometimes be invasive for the patient, occlude the radiographic picture, and end up projected outside the imaging sensor area in oblique protocols. Two possible frameworks are envisioned: a spatially shifting X-ray anode around the patient/object and a moving patient that moves/rotates while the imaging system remains fixed. As a proof of concept, experiences with a device under test (DUT), an anthropomorphic phantom and a real brachytherapy session have been carried out. The results show that it is possible to identify common points with a proper level of accuracy and retrieve three-dimensional locations, lengths and shapes with a millimetric level of precision. The presented approach is simple and compatible with both current and legacy widespread diagnostic X-ray imaging deployments and it can represent a good and inexpensive alternative to other radiological modalities like CT.

People re-identification in uncontrolled scenarios is a difficult task since people appearance may significantly vary along time due to changes in illumination, changes in the person pose or the presence of undesired objects in the scene. In order to cope with this temporal variability in the person appearance, we introduce the concept of Bags of Appearances (BoA) to describe each person. A BoA is a container of color features that fully represents a person by collecting all their different appearances along time. Matching of bags is performed in a probabilistic framework by accumulating the probability of matching for all of the elements of each bag. Experiments have been conducted in a real shop where clients were re-identified at the entrance and exit. Results improve state-of-the art methods and confirm that our proposal successfully copes with rough changes in the people appearance.

Most face recognition algorithms make only use of intensity information of the images discarding color as a distinctive cue. This paper extends the HOG-EBGM face recognition algorithm to use color information. In HOG-EBGM, each face is represented by a graph described by HOG features at specific landmarks. The color extension of the method here proposed intends to make the algorithm robust against color changes, while keeping its former robustness against scale, position, rotation and intensity variations. In the paper, several color representations of the faces are studied. Also, to reduce the higher dimensionality of the new color features, a comparison of dimensionality reduction techniques is included. Results on the Experiment 4 of the Face Recognition Grand Challenge show that color HOG-EBGM outperforms the gray-scale version of the algorithm in all cases. The best results were obtained using the Opponent color space with LDA.

This paper presents a video-based approach to traffic analysis and monitoring in night light conditions. In this kind of scenarios the headlights of the vehicles are the main features of the image taken from an urban or inter-urban traffic camera. The body of the vehicles is very low contrasted and many of the algorithms used in day-time decrease their performance. In our algorithm, we detect car headlights, and using this information, we obtain the three main magnitudes used in traffic monitoring: number of vehicles per time unit, i.e. intensity, mean speed, and occupancy. Extensive evaluations show that the system exhibits an excellent performance with real-time video sequences from cameras of the Traffic Authority of the city of Valencia, Spain.

This paper presents a video-based approach to detect the presence of parked vehicles in street lanes. Potential applications include the detection of illegally and double-parked vehicles in urban scenarios and incident detection on roads. The technique extracts information from low-level feature points (Harris corners) to create spatiotemporal maps that describe what is happening in the scene. The method neither relies on background subtraction nor performs any form of object tracking. The system has been evaluated using private and public data sets and has proven to be robust against common difficulties found in closed-circuit television video, such as varying illumination, camera vibration, the presence of momentary occlusion by other vehicles, and high noise levels.

This paper compares several approaches to extract facial landmarks and studies their influence on face recognition problems. In order to obtain fair comparisons, we use the same number of facial landmarks and the same type of descriptors (HOG descriptors) for each approach. The comparative results are obtained using FERET and FRGC datasets and show that better recognition rates are obtained when landmarks are located at real facial fiducial points. However, if the automatic detection of these is compromised by the difficulty of the images, better results are obtained using fixed landmarks grids.

This paper presents an approach to count the number of people that enters or leaves metro trains. This is a challenging scenario where usually people crowd around the train doors, and therefore it is not possible a direct approach that segments and counts individuals. The proposed technique is based on a statistical analysis of the flow obtained from the motion vectors at corner points. The method has been evaluated on metro sequences showing an average error below 5% in real operational conditions.

This paper presents a comparison between a new face recognition algorithm based on EBGM which replaces Gabor features by HOG descriptors and the original EBGM. The experiments results show a better performance behavior using public available databases. This better performance is explained by the properties of HOG descriptors which are more robust to changes in illumination, rotation and small displacements, and to the higher accuracy of the face graphs obtained compared to classical Gabor-EBGM ones.

This paper presents a system that labels TV shots either as commercial or program shots. The system uses two observations: logo presence and shot duration. These observations are modeled using HMMs, and a Viterbi decoder is finally used for shot labeling. The system has been tested on several hours of real video, achieving more than 99% correct labeling.

In this paper, we describe an approach that uses a combination of visual and audio features to cluster shots belonging to the same person in video programs. We use color histograms extracted from keyframes and faces, as well as cepstral coefficients derived from audio to calculate pairwise shot distances. These distances are then normalized and combined to a single confidence value which reflects our certainty that two shots contain the same person. We then use an agglomerative clustering algorithm to cluster shots based on these confidence values. We report the results of our system on a data set of approximately 8 hours of programming.

In this paper, we describe a unique new paradigm for video database management known as ViBE (video indexing and browsing environment). ViBE is a browseable/searchable paradigm for organizing video data containing a large number of sequences. The system first segments video sequences into shots by using a new feature vector known as the Generalized Trace obtained from the DC-sequence of the compressed data. Each video shot is then represented by a hierarchical structure known as the shot tree. The shots are then classified into pseudo-semantic classes that describe the shot content. Finally, the results are presented to the user in an active browsing environment using a similarity pyramid data structure. The similarity pyramid allows the user to view the video database at various levels of detail. The user can also define semantic classes and reorganize the browsing environment based on relevance feedback. We describe how ViBE performs on a database of MPEG sequences.

We describe a video indexing system that automatically searches for a specific person in a news sequence. The proposed approach combines audio and video confidence values extracted from speaker and face recognition analysis. The system also incorporates a shot selection module that seeks for anchors, where the person on the scene is likely speaking. The system has been extensively tested on several news sequences with very good recognition rates.

The objective of this work is the integration and optimization of an automatic face detection and recognition system for video indexing applications. The system is composed of a face detection stage presented previously which provides good results maintaining a low computational cost. The recognition stage is based on the Principal Components Analysis (PCA) approach which has been modified to cope with the video indexing application. After the integration of the two stages, several improvements are proposed which increase the face detection and recognition rate and the overall performance of the system. Good results have been obtained using the MPEG-7 video content set used in the MPEG-7 evaluation group.

In this paper we address the problem of reducing the amount of data to be analyzed when indexing audiovisual secuences. The reduction is based in selecting those parts of the video sequence where it is likely that there is a face talking. This can be useful since usually this kind of scenes contain important and reusable information such as interviews. The proposed technique is based on our a priori knowledge of the editing techniques used in news sequences. The results show that with this algorithm it is possible to discard arround 76% of the news sequence with minimal processing.

We address the problem of detecting shots of subjects that are interviewed in news sequences. This is useful since usually these kinds of scenes contain important and reusable information that can be used for other news programs. In a previous paper, we presented a technique based on a priori knowledge of the editing techniques used in news sequences which allowed a fast search of news stories. We present a new shot descriptor technique which improves the previous search results by using a simple, yet efficient algorithm, based on the information contained in consecutive frames. Results are provided which prove the validity of the approach.

The objective of this paper is to show that for every color space there exists an optimum skin detector scheme such that the performance of all these skin detectors schemes is the same. To that end, a theoretical proof is provided and experiments are presented which show that the separability of the skin and no skin classes is independent of the color space chosen.

This paper presents an unsupervised color segmentation technique to divide skin detected pixels into a set of homogeneous regions which can be used in face detection applications or any other application which may require color segmentation. The algorithm is carried out in a two stage processing, where the chrominance and luminance information are used consecutively. For each stage a novel algorithm which combines pixel and region based color segmentation techniques is used. The algorithm has proven to be effective under a large number of test images.

The objective of this work is to provide a simple and yet efficient tool to detect human faces in video sequences. This information can be very useful for many applications such as video indexing and video browsing. In particular the paper focuses on the significant improvements made to our face detection algorithm presented by Albiol, Bouman and Delp (see IEEE Int. Conference on Image Processing, Kobe, Japan, 1999). Specifically, a novel approach to retrieve skin-like homogeneous regions is presented, which is later used to retrieve face images. Good results have been obtained for a large variety of video sequences.

Pseudo-semantic labeling represents a novel approach for automatic content description of video. This information can be used in the context of a video database to improve browsing and searching. In this paper we describe our work on using face detection techniques for pseudo-semantic labeling. We present our results using a database of MPEG sequences.