Italy

Training machine learning models in a supervised manner
requires vast amounts of labeled data, where the labels are typically
provided by humans manually annotating samples using a variety of
tools. In this work, an intelligent annotation tool is proposed to combine
the fast and efficient labeling capabilities of modern machine learning
models with the reliable and accurate but slow correction capabilities of
human annotators. For the example of instance segmentation in videos,
techniques to interactively condition a model on previously predicted
and manually annotated (corrected) frames are explored to create an
iterative workflow combining the advantages of the intelligent model and
the human annotator. Thereby, the intelligent model conducts the bulk
of the work, performing instance detection, tracking, and segmentation,
and enables the human annotator to correct individual frames selectively
and instances. The proposed approach is based on the one-shot learning
paradigm, and, thus, avoids the computational cost of online retraining.
For this purpose, we use Siamese neural networks to transfer annotations
from one video frame to another. Multiple interaction options regarding
the choice of the additional input data to the neural network, e.g., model
predictions or manual corrections, are explored to refine the labeling
performance of the given model and speed up the annotation process.

ICPR 2020

Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks

video annotation

instance detection

tracking

segmentation

semi-supervised

labeling

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


technical paper

State-of-the-art instance segmentation techniques currently provide a bounding box, class, mask, and scores for each instance. What they do not provide is an epistemic uncertainty estimate of these predictions. With our approach, we want to identify corner cases by considering the epistemic uncertainty. Corner cases are data/situations that are underrepresented or not covered in our data set. Our work is based on Mask R-CNN. We estimate the epistemic uncertainty by extending the architecture with Monte-Carlo dropout layers. By repeatedly executing the forward pass, we create a large number of predictions per instance. Afterward, we cluster the predictions of an instance based on the bounding box coordinates. It becomes possible to determine the epistemic position uncertainty for the bounding boxes and the classifier's epistemic class uncertainty. For the epistemic uncertainty regarding the bounding box position and the class assignment, we provide a criterion for detecting corner cases utilizing the model's epistemic uncertainty.

Towards Corner Case Detection by Modeling the Uncertainty of Instance Segmentation Networks

We present an approach for driver identification, which is useful in many automotive applications such as safety or comfort functions. Driver identification would also be of great interest to other business models, such as car rental and car-sharing companies. The identification method is based on the driver's physiological state or rather his/her electrocardiogram (ECG) data. For this purpose, we have recorded ECG data of 25 people driving in a simulated environment. To identify a driver, we extend our existing novelty detection by aggregating local features over time. To do so, we extracted features and trained a Gaussian Mixture Model (GMM) to exploit localities present in the recorded sensor data. With novelty detection by aggregating local features, we are smoothing the noisy signal and reducing the dimensionality for further processing in a one-class SVM classification. Based on the output, a decision function decides whether the driver is unknown or well-known, and if the driver is well-known, who of the known driver is it.

Novelty based Driver Identification on RR Intervals from ECG Data

In the era of industry 4.0, factories around the world are developing towards automation and artificial intelligence, in which industrial detection plays an important role. After the cutting process, the surface of a stainless steel plate may produce various defects, such as scratches, chisels, and stains. Due to the characteristic of bright reflections on the surface of a stainless steel plate, the traditional manual comparison detection method is time-consuming, laborious, and prone to different detection results due to the interference of high reflection, resulting in the outflow of defective products. This paper used existing mature deep learning models for object detection, YOLOv3(You Only Look Once) and SSD(Single Shot MultiBox Detector), which are the base network architectures for the defect detection of stainless steel plates, in order to eeffectively improve the accuracy of stainless steel plate detection. Through image preprocessing, the relative positions of sample defects are marked to improve data processing before training, in order that a large number of image samples can be quickly and effectively processed for training.

Defect Detection of Stainless Steel Plates Using Deep Learning Technology

Semantic segmentation and shape detection of lumbar vertebrae, sacrum, and femoral heads from clinical X-ray images are important and challenging tasks. In this paper, we propose a new multi-path convolutional neural network, BiLuNet, for semantic segmentation on X-ray images. The network is capable of medical image segmentation with very limited training data. With the shape fitting of the bones, we can identify the location of the target regions very accurately for lumbar vertebra inspection. We collected our dataset and annotated by doctors for model training and performance evaluation. Compared to the state-of-the-art methods, the proposed technique provides better mIoUs and higher success rates with the same training data. The experimental results have demonstrated the feasibility of our network to perform semantic segmentation for lumbar vertebrae, sacrum, and femoral heads.

BiLuNet: A Multi-path Network for Semantic Segmentation on X-ray Images

The presentation reviews the work and demonstrates the purposed hybrid machine learning techniques to predict the energy consumption with multi-source data.

A Hybrid Machine Learning Approach for Energy Consumption Prediction in Additive Manufacturing

We present a multiregion image segmentation approach which utilizes multiscale anisotropic diffusion based scale spaces. By combining powerful edge preserving anisotropic diffusion smoothing with isolevel set linking and merging, we obtain coherent segments which are tracked across multiple scales. A hierarchical tree representation of the given input image with progressively simplified regions is used with intra-scale splitting and inter-scale merging for obtaining multiregion segmentations. Experimental results on natural and medical images indicate that multiregion, multiscale image segmentation (MMIS) approach obtains coherent segmentation results.

Multiregion multiscale image segmentation with anisotropic diffusion

Deep-learning-based methods have been used for 3D action recognition in recent years. Methods based on recurrent neural networks (RNNs) have the advantage of modeling long-term context, but they fo- cus mainly on temporal information and ignore the spatial relationships in each skeleton frame. In addition, it is difficult to handle a very long skeleton sequence using an RNN. Compared with an RNN, a convolu- tional neural network (CNN) is better able to extract spatial information. To model the temporal information of skeleton sequences and incorpo- rate the spatial relationship in each frame efficiently using a CNN, this paper proposes a multi-feature skeleton representation for encoding fea- tures from original skeleton sequences. The relative distances between joints in each skeleton frame are computed from the original skeleton sequence, and several relative angles between the skeleton structures are computed. This useful information from the original skeleton sequence is encoded as pixels in grayscale images. To preserve more spatial re- lationships between input skeleton joints in these images, the skeleton joints are divided into five groups: one for the trunk and one for each arm and each leg. Relationships between joints in the same group are more relevant than those between joints in different groups. By rear- ranging pixels in encoded images, the joints that are mutually related in the spatial structure are adjacent in the images. The skeleton repre- sentations, composed of several grayscale images, are input to CNNs for action recognition. Experimental results demonstrate the effectiveness of the proposed method on three public 3D skeleton-based action datasets.

A Novel Multi-Feature Skeleton Representation for 3D Action Recognition

Semantic segmentation is always a key problem in remote sensing image analysis. Especially, it is very useful for city-scale vehicle detection. However, multi-object and imbalanced data classes of remote sensing images bring a huge challenge, which leads that many traditional segmentation approaches were often unsatisfactory. In this paper, we propose a novel Refined Semantic Segmentation Network (R2SN), which apply the classic encoder-to-decoder framework to handle segmentation problem. However, we add the convolution layers in encoder and decoder to make the network can achieve more local information in the training step. The design is more suitable for high-resolution remote sensing image. More specially, the classic Focal loss is introduced in this network, which can guide the model focus on the difficult objects in remote sensing images and effectively handle multi-object segmentation problem. Meanwhile, the classic Hinge loss is also utilized to increase the distinction between classes, which can guarantee the more refined segmentation results. We validate our approach on the International Society for Photogrammetry and Remote Sensing (ISPRS) semantic segmentation benchmark dataset. The evaluation and comparison results show that our method exceeds the state-of-the-art remote sensing image segmentation methods in terms of mean intersection over union (MIoU), pixel accuracy, and F1-score.

Refined Semantic Segmentation Network of City Remote Sensing Image

In our work, we focused on face identification from thermal images. Thermal face identification brings several advantages such as ease of handling with low resolution images, robust to illumination and privacy preserving.
Moreover, we considered scenarios in which face identification from thermal images is performed with low computation and memory resources, making such systems suitable for mobile or embedded applications such as STM32F7 family microcontroller.

Real-Time Thermal Face Identification System for Low Memory Vision Applications Using CNN

In this work we use two approaches to prevent double spend-
ing and secure IoT transaction through Blockchain and information fu-
sion techniques: the rst method is based on Smart Contracts; while
the second method is implemented by a novel Blockchain system. Both
methods use a hybrid RSA and biometric codes fusion in order to have
an encrypted, taking account of the privacy, identity of the spender. In
Blockchain a contract between the parties is stipulated and the biomet-
ric fused code are kept. The used coin pack is tagged, so a future double
spending or any illegal action on the IoT network or Smart city becomes
forbidden and prosecutable legally. The second part of the work will
present a novel Blockchain where a transaction can be signed only if the
user is successfully authenticated though his biometric fused key.

Premium content

Intelligent and Interactive Video Annotation for Instance Segmentation using Siamese Neural Networks

Downloads

Next from ICPR 2020

Towards Corner Case Detection by Modeling the Uncertainty of Instance Segmentation Networks

Similar lecture

Tracking Fast Moving Objects by SegmentationNetwork