Italy

People counting concentrates on predicting the number of people in surveillance images. It remains challenging due to the rich variations in scene type and crowd density. Besides, the limited closed-set with ground truth from reality significantly increase the difficulty of people counting in actual open-set. Targeting to solve these problems, this paper proposes a domain adaptation people counting via style-level transfer learning (STL) and scene-aware estimation (SAE). The style-level transfer learning explicitly leverages the style constraint and content similarity between images to learn effective knowledge transfer, which narrows the gap between closed-set and open-set by generating domain adaptation images. The scene-aware estimation introduces scene classifier to provide scene-aware weights for adaptively fusing density maps, which alleviates interference of variations in scene type and crowd density on domain adaptation people counting. Extensive experimental results demonstrate that images generated by STL are more suitable for domain adaptation learning and our proposed approach significantly outperforms the state-of-the-art methods on multiple cross-domain pairs.

ICPR 2020

DAPC: Domain Adaptation People Counting via
Style-level Transfer Learning and Scene-aware

scene-aware estimation

people counting; domain adaptation; style-level transfer learning

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. 


poster

In this paper, we propose a method to detect various types of lane markings and road boundaries simultaneously from a monocular camera image. This method detects lane markings and road boundaries in IPM images obtained by the Inverse Perspective Mapping of input images. First, bounding boxes surrounding a lane marking or the road boundary are extracted by the object detection network. At the same time, these areas are labelled with a solid line, a dashed line, a zebra line, a curb, grass, a sidewall and so on. Next, in each bounding box, lane marking boundaries or road boundaries are drawn by the image-to-image translation network. We use YOLOv3 for the object detection and pix2pix for the image translation. We create our own datasets including various types of lane markings and road boundaries
and evaluate our approach using these datasets qualitatively and quantitatively.

Lane Detection based on Object Detection and Image-to-image Translation


Segmentation-based approaches have enabled stateof-the-art performance in long or curved text detection tasks.However, false detection still is a challenge when two text instances are close to each other. To address this problem, in this paper, we propose a Text Contour Attention Text Detector (TCATD), which can locate scene text with arbitrary orientation and shape accurately. Different from previous work, TCATD focus on text contour map (TC), text center intensity map (TCI) and text kernel maps (TK). The TC can introduce text contour information, the TCI can help to learn the accurate text segmentation and the TK can generate the complete shape of text instances. Besides, we propose a Text Contour ttention Module to deal with contour information. After the Text Contour Attention Module, TC, TCI and TK will be obtained. Extensive experiments on ICDAR2015, CTW1500 and Total-Text demonstrate that the proposed method achieves the state-of-theart performance.

TCATD: Text Contour Attention for Scene Text Detection 


Since the convolutional neural networks are often trained with redundant parameters, it is possible to reduce redundant kernels or filters to obtain a compact network without dropping the classification accuracy.
Such methods are called structure pruning.
In this paper, we propose a filter pruning method using the hierarchical group sparse regularization. 
It is shown in our previous work that the hierarchical group sparse regularization is effective in obtaining sparse networks in which filters connected to unnecessary channels are automatically close to zero.
After training the convolutional neural network with the hierarchical group sparse regularization, the unnecessary filters are selected based on the increase of the classification loss of the randomly selected training samples to obtain a compact network.
It is shown that the proposed method can reduce more than 50% parameters of ResNet for CIFAR-10 with only 0.3% decrease in the accuracy of test samples.
Also, 34% parameters of ResNet are reduced for TinyImageNet-200 with higher accuracy than the
baseline network.

Filter Pruning using Hierarchical Group Sparse Regularization for Deep Convolutional Neural Networks

Human Pose Estimation is a low-level task useful forsurveillance, human action recognition, and scene understandingat large. It also offers promising perspectives for the animationof synthetic characters. For all these applications, and especiallythe latter, estimating the positions of many joints is desirablefor improved performance and realism. To this purpose, wepropose a novel method called JUMPS for increasing the numberof joints in 2D pose estimates and recovering occluded ormissing joints. We believe this is the first attempt to addressthe issue. We build on a deep generative model that combines a Generative Adversarial Network (GAN) and an encoder. TheGAN learns the distribution of high-resolution human posesequences, the encoder maps the input low-resolution sequencesto its latent space. Inpainting is obtained by computing the latentrepresentation whose decoding by the GAN generator optimallymatches the joints locations at the input. Post-processing a 2Dpose sequence using our method provides a richer representationof the character motion. We show experimentally that thelocalization accuracy of the additional joints is on average onpar with the original pose estimates.

JUMPS: Joints Upsampling Method for Pose Sequences


Alpha matting aims to estimate the translucency of an object in a given image. The resulting alpha matte describes pixel-wise to what amount foreground and background colors contribute to the color of the composite image. While most methods in literature focus on estimating the alpha matte, the process of estimating the foreground colors given the input image and its alpha matte is often neglected, although foreground estimation is an essential part of many image editing workflows. In this work, we propose a novel method for foreground estimation given the alpha matte. We demonstrate that our fast multi-level approach yields results that are comparable with the state-of-the-art while outperforming those methods in computational runtime and memory usage.

Fast Multi-Level Foreground Estimation}


Methods developed for normal 2D text detection do not work well for text that is rendered using decorative, 3D effects, etc. This paper proposes a new method for classification of 2D and 3D natural scene text images so that an appropriate recognition method can be chosen accordingly based on the classification results for better performance. The proposed method explores local gradient differences for obtaining candidate pixels, which represent a stroke. To study the spatial distribution of candidate pixels, we propose a measure, called COLD, which is denser for pixels toward the center of strokes and scattered for non-stroke pixels. This observation leads us to introduce mass features for extracting the regular spatial pattern of COLD, which indicates a 2D text image. The extracted features are fed into a Neural Network (NN) for classification. The proposed method is tested on (i) a new dataset introduced in this work (ii) a second dataset assembled from standard natural scene datasets (iii) Non-Text Image datasets which does not contain text, rather it contains objects. Experimental results of the proposed method on images with text and non-text show that the proposed method is independent of text. The proposed approach improves text detection and recognition performance significantly after classification.

Local Gradient Difference Features for Classification of 2D-3D Natural Scene Text Images


In myocardium segmentation of cardiac magnetic resonance images, ambiguities often appear near the boundaries of the target domains due to tissue similarities. To address this issue, we propose a new architecture, called FOANet, which can be decomposed in three main steps: a localization step, a Gaussian-based contrast enhancement step, and a segmentation step. This architecture is supplied with a hybrid loss function that guides the FOANet to study the transformation relationship between the input image and the corresponding label in a three-level hierarchy (pixel-, patch- and map-level), which is helpful to improve segmentation and recovery of the boundaries. We demonstrate the efficiency of our approach on two public datasets in terms of regional and boundary segmentations.

FOANet: A Focus of Attention Network with Application to Myocardium Segmentation


Gaussian smoothing and its first and second differentials are very important for image processing and computer vision. We already have methods based on the sliding Fourier transform (SFT) in order to calculate Gaussian smoothing efficiently. However, errors in floating point calculation accumulate quickly when we use the single-precision floating-point format. Also, the resultant discontinuities at the edges of SFT intervals generate false extreme points easily. To resolve the above-mentioned problems, we propose the attenuated SFT (ASFT) by introducing a decay factor to the original SFT together with a new criterion for determining coefficients to effectively approximate Gaussian function and its differentials. Extensive experiments demonstrate a decisive superiority of the proposed ASFT over the original SFT.

Stabilized Calculation of Gaussian Smoothing and Its Differentials Using Attenuated Sliding Fourier Transform

In this paper we consider a collection of relative pose problems which arise naturally in applications for visual indoor navigation using unmanned aerial vehicles~(UAVs). We focus on cases where additional information from an onboard IMU is available and thus provides a partial extrinsic calibration through the gravitational vector. 
The solvers are designed for a partially calibrated camera, for a variety of realistic indoor scenarios, which makes it possible to navigate using images of the ground floor. Current state-of-the-art solvers use more general assumptions, such as using arbitrary planar structures; however, these solvers do not yield adequate reconstructions for real scenes, nor do they perform fast enough to be incorporated in real-time systems.

We show that the proposed solvers enjoy better numerical stability, are faster, and require fewer point correspondences, compared to state-of-the-art approaches. These properties are vital components for robust navigation in real-time systems, and we demonstrate on both synthetic and real data that our method outperforms other solvers, and yields superior motion estimation.


Minimal Solvers for Indoor UAV Positioning

we focus on Universal Adversarial Perturbations(UAP)attack on state-of-the-art person re-identification (Re-ID) methods. Existing UAP methods usually compute a perturbation image and add it to the images of interest. Such a simple constant form greatly limits the attack power. To address this problem, we extend the formulation of UAP to a polynomial form and propose the Polynomial Universal Adversarial Perturbation (PUAP). Unlike traditional UAP methods which only rely on the additive perturbation signal, the proposed PUAP consists of both an additive perturbation and a multiplicative modulation factor. The additive perturbation produces the fundamental component of the signal, while the multiplicative factor modulates the perturbation signal in line with the unit impulse pattern of the input image. Moreover, we introduce a Pearson correlation coefficient loss to generate universal perturbations, for disrupting the outputs of person Re-ID models. Extensive experiments on DukeMTMCreID, Market-1501, and MARS show that the proposed method can efficiently improve the attack performance.

Downloads

Next from ICPR 2020

Lane Detection based on Object Detection and Image-to-image Translation

Similar lecture

Nested Attention U-Net (NAU-N): A Splicing Detection Method for Satellite Images