Object detectors are central to autonomous driving and are widely used in driver assistance systems. Object detectors are trained on a finite amount of data within a specific domain, hampering detection performance when applying object detectors to samples from other domains during inference, an effect known as domain gap. Domain gap is a concern for data-driven applications, evoking repetitive retraining of networks when the applications unfold into other domains. With object detectors that have been trained on day images only, a domain gap can be observed in object detection by night. Training object detectors on night images is critical because of the enormous effort required to generate an adequate amount of diversely labeled data, and existing data sets often tend to overfit specific domain characteristics. For the first time, this work proposes adapting domains by online image-to-image translation to expand an object detector's domain of operation. The domain gap is decreased without additional labeling effort and without having to retrain the object detector while unfolding into the target domain. The approach follows the concept of domain adaptation, shifting the target domain samples into the domain knownto the object detector (source domain). Firstly, the UNIT network is trained for domain adaptation and subsequently cast into an online domain adaptation module, which narrows down the domain gap. Domain adaptation capabilities are evaluated qualitatively by displaying translated samples and visualizing the domain shift through the 2D tSNE algorithm. We quantitatively benchmark the domain adaptation's influence on a state-of-the-art object detector, and on a retrained object detector, for mean average precision, mean recall, and the resulting F1-score. Our approach achieves an F1 score improvement of $5.27 \%$ within object detection by night when applying online domain adaptation. The evaluation is executed on the BDD100K benchmark data set.

Night-to-Day: Online Image-to-Image Translation for Object Detection Within Autonomous Driving by Night

Existing studies using visible-light cameras have mainly focused on methods of pedestrian detection during daytime. However, these studies found it difficult to detect pedestrians during nighttime with low external light. The NIR illuminator has limitations in terms of illumination angle and distance, and the illuminator's power needs to be adjusted depending on whether an object is near or distant. Although, thermal cameras were used for nighttime pedestrian detection, thermal cameras are currently expensive and thus difficult to install in many places. To solve these problems, attempts have been made to use visible-light cameras for nighttime pedestrian detection. However, most of these attempts considered an indoor environment where the distance to the object was short. This study proposes a method of pedestrian detection at nighttime using a visible-light camera and faster region-based convolutional neural network (R-CNN). In addition, as pedestrians cannot be reliably detected from a single nighttime image, we combined deep convolutional features in successive frames. Using Korea advanced institute of science and technology (KAIST) open database, we conducted experiments and observed that the proposed method performed better than the baseline methods at all times (day and night). In addition, through the experiments with national ICT Australia Ltd. (NICTA) open database, we confirm that the proposed method is effective for pedestrian detection at all times. Finally, we present theoretical grounds for the proposed fusion.

Pedestrian detection based on faster R-CNN in nighttime by fusing deep convolutional features of successive images

A computing system utilizing coordinated two-hand command gestures. An embodiment of an apparatus includes a sensing element to sense a presence or movement of a user of the apparatus, including the sensing of command gestures by the user to provide input to the apparatus, a processor, wherein operation of the processor includes interpretation of the command gestures of the user and the implementation of actions in response to the command gestures, and a display screen to display elements to the user, where the display screen may display one or more elements use in command gestures, where command gestures include coordinated two-hand command gestures of the user.

Computing system utilizing coordinated two-hand command gestures

Gesture recognition is an important part of human-robot interaction. In order to achieve fast and stable gesture recognition in real time without distance restrictions, this paper presents an improved threshold segmentation method. The improved method combines the depth information and color information of a target scene with hand position by the spatial hierarchical scanning method; the ROI in the scene is thus extracted by the local neighbor method. In this way, the hand can be identified quickly and accurately in complex scenes and different distances. Furthermore, the convex hull detection algorithm is used to identify the positioning of fingertips in ROI, so that the fingertips can be identified and located accurately. The experimental results show that the hand position can be obtained quickly and accurately in the complex background by using the improved method, the real-time recognition distance interval can be reached by 0.5 m to 2.0 m, and the fingertip detection rates can be reached 98.5% in average. Moreover, the gesture recognition rates are more than 96% by the convex hull detection algorithm. It can be thus concluded that the proposed method achieves good performance of hand detection and positioning at different distances.

/pdf/kinect-sensor-based-long-distance-hand-gesture-recognition-s0iej2lud5.pdf

Kinect Sensor-Based Long-Distance Hand Gesture Recognition and Fingertip Detection with Depth Information

A comprehensive survey on digital video forensics: Taxonomy, challenges, and future directions

Robust and real time moving object tracking is a tricky job in computer vision problems. Particle filtering has been proven very successful for non-Gaussian and non-linear estimation problems. In this paper, we first try to develop a color based particle filter. In this approach, the object tracking system relies on the deterministic search of window, whose color content matches a reference histogram model. A simple HSV histogram-based color model is used to develop our observation system. Secondly and finally, we describe a new approach for moving object tracking with particle filter by shape information. The shape similarity between a template and estimated regions in the video scene is measured by their normalized cross-correlation of distance transformed image. Our observation system of particle filter is based on shape from distance transformed edge features. Template is created instantly by selecting any object from the video scene by a rectangle. Experimental results have been presented to show the effectiveness of our proposed system.

Real Time Moving Object Tracking by Particle Filter

A mobile terminal and touch recognizing method therein are disclosed, by which a multi-touch can be recognized. The present invention includes receiving a plurality of touches simultaneously using a touchscreen, consecutively receiving a plurality of images including a plurality of the received touches for a predetermined time using a camera provided under the touchscreen, determining patterns and pattern changes of a plurality of the touches included in a plurality of the images, respectively, and recognizing a gesture by a plurality of the touches in accordance with a result of the determining step. Moreover, the touch pattern includes at least one selected from the group consisting of a touch number, a touch point, a touch size and a touch figure.

Mobile terminal and touch recognizing method therein

In this paper, we propose an approach for object recognition using binary local invariant features and color information. In our approach, we use a fast detector for key point detection and binary local features descriptor for key point description. For local feature matching, the Fast library for Approximated Nearest Neighbors (FLANN) is applied to match the query image and reference image in data set. A homography matrix which represents transformation of object in scene image and reference image is estimated from matching pairs by using the Optimized Random Sample Consensus Algorithm (ORSA). Then, we detect object location in the image, and remove background of image. Next, significant color feature is used to calculate global color histogram since it reflects main content of primitive image and also ignores noises. Similarity of query image and reference object image is a linear combination of color histogram correlation and number of feature matches. As a result, the proposed method can overcome drawbacks of object recognition method using only local features or global features. In addition, the use of binary feature makes feature description as well as feature matching faster to meet the requirement of a real time system. For evaluation, we experiment with two well-known and latest local invariant features including the Oriented Fast and Rotated Binary Robust Independent Elementary Features (ORB) and Fast Retina Key point (FREAK) and a planar object data set. According to the result, ORB feature shows that it is powerful as our system obtained the higher accuracy and fast processing time. The experimental results also proved that combination of binary local invariant feature and significant color is effective for planar object recognition.

Object Recognition by Combining Binary Local Invariant Features and Color Histogram

Detecting moving objects based on the camera attached in mobile robot is not trivial since both background and object are moving independently. For moving object detection the movement of moving object needs to be extracted by considering the background which has also changed by the ego-motion of mobile robot. Affine transformation is widely used to estimate the background transformation between images. However when using omnidirectional camera, the mixed motion of scaling, rotation and translation appears in local areas and single affine transformation is not sufficient to describe those mixed nonlinear motions. In this paper, the proposed method divides the image as grid windows and obtains each affine transform for each window. This method can obtain stable background transformation when the background has few corner features. The area of moving objects can be obtained from the background transformation-compensated frame difference using every local affine transformation for each local window. The experimental results demonstrate the proposed method is very efficient in moving object detection in mobile robot environment.

Moving object detection in omnidirectional vision-based mobile robot

This paper presents a gesture recognition interface with the observed pose sequence determined by our upper body model-based pose tracking. For last decade many researchers have focused on how well tracks human poses based on predefined pose model. Then we move this discussion to the gesture recognition by pose tracking. Our system consists of two parts: pose tracking and gesture recognition. In the first part, Particle filtering is used for tracking the upper body pose with the key pose library where we try to find key pose for the proposal distribution. The particles generated from the proposal distribution with random noise, could cover the pose space which is not covered by the key pose library. In second part, the observed pose is labeled with a pose number among all key poses by comparing between key poses. HMM is used to determine the probabilities of the gesture states from the observed pose sequence. HMM parameters like transition and emission matrix are trained by the analysis on the gesture database. The experimental results shows how well gesture recognition works based on our system.

A gesture recognition interface with upper body model-based pose tracking

Popular Tasks used by Researchers

How can I help with your research?

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

We encountered an error while loading the panel. Please try refreshing the page.

Something went wrong

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

Anyone with the link can view this chat. You can switch it back to private anytime.

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Chi-Min Oh

Author Tools

Chat about Author