Consistent Semantic Annotation of Outdoor Datasets via 2D/3D Label Transfer

The advance of scene understanding methods based on machine learning relies on the availability of large ground truth datasets, which are essential for their training and evaluation. Construction of such datasets with imagery from real sensor data however typically requires much manual annotation of semantic regions in the data, delivered by substantial human labour. To speed up this process, we propose a framework for semantic annotation of scenes captured by moving camera(s), e.g., mounted on a vehicle or robot. It makes use of an available 3D model of the traversed scene to project segmented 3D objects into each camera frame to obtain an initial annotation of the associated 2D image, which is followed by manual refinement by the user. The refined annotation can be transferred to the next consecutive frame using optical flow estimation. We have evaluated the efficiency of the proposed framework during the production of a labelled outdoor dataset. The analysis of annotation times shows that up to 43% less effort is required on average, and the consistency of the labelling is also improved.

Effective Flicker Detection Technique Using Artificial Neural Network For Video

Flicker is the most common and an intolerable blemish present in signal processing world that leads to distortion in the transmitted frame of a video string. To dodge such misinterpretations a technique for detection of the flickering frame in a video is depicted in this research. Earlier methods were based on removing flicker by calculating the threshold of the consecutive frame difference and then finding the flickering frame. The proposed method in this research includes finding flickering frame using neural network concept. Therefore, the advantage of the practice disclosed here is that it removes the tedious calculation part of the threshold value and thereby the computational part becomes easier with added accurate result.

Real-time Foreground Object Detection Combining the PBAS Background Modelling Algorithm and Feedback from Scene Analysis Module

The article presents a hardware implementation of the foreground object detection algorithm PBAS (Pixel-Based Adaptive Segmenter) with a scene analysis module. A mechanism for static object detection is proposed, which is based on consecutive frame differencing. The method allows to distinguish stopped foreground objects (e.g. a car at the intersection, abandoned luggage) from false detections (so-called ghosts) using edge similarity. The improved algorithm was compared with the original version on popular test sequences from the changedetection.net dataset. The obtained results indicate that the proposed approach allows to improve the performance of the method for sequences with the stopped objects. The algorithm has been implemented and successfully verified on a hardware platform with Virtex 7 FPGA device. The PBAS segmentation, consecutive frame differencing, Sobel edge detection and advanced one-pass connected component analysis modules were designed. The system is capable of processing 50 frames with a resolution of 720 × 576 pixels per second

Top-Down and Bottom-Up Cues Based Moving Object Detection for Varied Background Video Sequences

Moving object detection is a crucial and critical task for any surveillance system. Conventionally, a moving object detection task is performed on the basis of consecutive frame difference or background models which are based on some mathematical aspects or probabilistic approaches. But, these approaches are based on some initial conditions and short amount of time is needed to learn all these models. Also, the bottleneck in all these previous approaches is that they require neat and clean background or need to create a background first by using some approaches and that it is essential to update them regularly to cope with the illuminating changes. In this paper, moving object detection is executed using visual attention where there is no need for background formulation and updates as it is background independent. Many bottom-up approaches and one combination of bottom-up and top-down approaches are proposed in the present paper. The proposed approaches seem more efficient due to inessential requirement of learning background model and due to being independent of previous video frames. Results indicate that the proposed approach works even against slight movements in the background and in various outdoor conditions.

Efficient Data Association for Multiple Vehicles Tracking

Data association problem has been an important issue for the multiple vehicles tracking in a vehicle tracking system. In this paper, we present an efficient data association method to track multiple vehicles in a sequence of traffic video frames. We first introduce the compact rectangular region-of-interest (crROI) that tightly encloses a vehicle and has the rotation-invariant property. The subsequent processing is based on the crROI instead of a vehicle image itself to avoid the processing overhead. Next, we extract the features from the crROI such as shape, size, and spatial relationship. Using these features, we define the similarity metric between two vehicles, and present the association method that matches a vehicle in a frame with the corresponding vehicle in its consecutive frame. An experimental result shows that the proposed method identifies and tracks vehicles effectively and efficiently in the curve or crossroad environment where multiple vehicles appear.