The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We present a novel method for detecting 3D model instances and estimating their 6D poses from RGB data in a single shot. To this end, we extend the popular SSD paradigm to cover the full 6D pose space and train on synthetic model data only. Our approach competes or surpasses current state-of-the-art methods that leverage RGBD data on multiple challenging datasets. Furthermore, our method produces...
In this paper, we propose a real-time detection algorithm using a MCT AdaBoost classifier which detects two-wheeler in a blind spot. The proposed algorithm uses a cascade classifier generated by AdaBoost learning based on the MCT feature vector. The MCT AdaBoost classifier is composed of weak classifiers as many as the number of pixels of the detection window, and each pixel becomes a weak classifier...
There is a large demand in the area of video-surveillance, especially in people detection, which has caused a large increase in the number of researches and resources in this field. As training images and annotations are not always available, it is important to consider the cost involved in creating the detector models. For example, for elderly people detection, the detector must have into account...
Action recognition is still a challenging problem. In order to catch effective compact representation of the action sequences, the discriminative dictionaries could be learned by sparse coding. But sparse coding is needed in both the training and testing phases of the classifier framework. And it is also time consuming for the adoption of 1-norm sparsity constraint on the representation coefficients...
Pedestrian detection is an important topic in object detection. Compared with other object detectors, YOLOv2 achieves high accuracy and fast speed for general object detection, however it degrades accuracy when detecting crowed pedestrians. In this paper, combining with the skip structure of FCN, we tailor the YOLOv2 network to improve the accuracy in detecting small pedestrians which appear in groups...
We present an Automatic License Plate Recognition system designed around Convolutional Neural Networks (CNNs) and trained over synthetic plate images. We first design CNNs suitable for plate and character detection, sharing a common architecture and training procedure. Then, we generate synthetic images that account for the varying illumination and pose conditions encountered with real plate images...
Nowadays, more and more methods have been proposed to solve the problem of face detection based on computer implementation. Due to the variations in background, illumination, pose and facial expressions, the problem of machine face detection is complex. Recently, deep learning approaches achieve an impressive performance on face detection. In this paper, a model named Multi-Scale Fusion Convolutional...
In light of the powerful learning capability of deep neural networks (DNNs), deep (convolutional) models have been built in recent years to address the task of salient object detection. Although training such deep saliency models can significantly improve the detection performance, it requires large-scale manual supervision in the form of pixel-level human annotation, which is highly labor-intensive...
While most existing approaches for detection in videos focus on objects or human actions separately, we aim at jointly detecting objects performing actions, such as cat eating or dog jumping. We introduce an end-to-end multitask objective that jointly learns object-action relationships. We compare it with different training objectives, validate its effectiveness for detecting objects-actions in videos,...
A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new environment with new instances requires expensive data collection and annotation. In this paper, we propose a simple approach to generate large annotated instance...
Weakly supervised object localization remains challenging, where only image labels instead of bounding boxes are available during training. Object proposal is an effective component in localization, but often computationally expensive and incapable of joint optimization with some of the remaining modules. In this paper, to the best of our knowledge, we for the first time integrate weakly supervised...
We define the object detection from imagery problem as estimating a very large but extremely sparse bounding box dependent probability distribution. Subsequently we identify a sparse distribution estimation scheme, Directed Sparse Sampling, and employ it in a single end-to-end CNN based detection model. This methodology extends and formalizes previous state-of-the-art detection models with an additional...
We describe a method to produce a network where current methods such as DeepFool have great difficulty producing adversarial samples. Our construction suggests some insights into how deep networks work. We provide a reasonable analyses that our construction is difficult to defeat, and show experimentally that our method is hard to defeat with both Type I and Type II attacks using several standard...
Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing work attempts to exploit temporal information on box level, but such methods are not trained end-to-end. We present flow-guided feature aggregation, an accurate and end-to-end learning...
Imagery texts are usually organized as a hierarchy of several visual elements, i.e. characters, words, text lines and text blocks. Among these elements, character is the most basic one for various languages such as Western, Chinese, Japanese, mathematical expression and etc. It is natural and convenient to construct a common text detection engine based on character detectors. However, training character...
We present a 1.62–5.4-Gb/s receiver for DisplayPort version 1.2a and propose an adaptive equalizer (EQ) with a peak-level comparison technique for eye measurement. A single comparator and an up/down unmatched-current charge pump are used to realize a simpler EQ architecture with low power dissipation. A referenceless frequency acquisition technique is also proposed. A time-to-digital converter-based...
The QRS complex detection methods have been extensively studied over the past several decades, and the current common QRS detection algorithms can achieve high detection accuracy on the open-access ECG database. Although massive of researches exist on the performance of QRS detectors, the effect of the ECG signal gain is usually ignored and did not attract researchers' attentions in the past studies...
The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. In...
Despite their success for object detection, convolutional neural networks are ill-equipped for incremental learning, i.e., adapting the original model trained on a set of classes to additionally detect objects of new classes, in the absence of the initial training data. They suffer from “catastrophic forgetting”–an abrupt degradation of performance on the original set of classes, when the training...
Learned boundary maps are known to outperform handcrafted ones as a basis for the watershed algorithm. We show, for the first time, how to train watershed computation jointly with boundary map prediction. The estimator for the merging priorities is cast as a neural network that is convolutional (over space) and recurrent (over iterations). The latter allows learning of complex shape priors. The method...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.