Search

Object detection is important in car sharing services. Accuracy, efficiency, and low memory consumption are desirable for object detection in car sharing services. This paper presents a network system that satisfies all these requirements. Our approach first divides the object detection task into multiple simpler local regression tasks. Then, we propose the generalized Haar filter-based convolutional neural network to reduce the consumption of memory and computing resource. To achieve real-time performance, we introduce a sparse window generation strategy to reduce the number of input image patches without sacrificing accuracy. We perform experiments on both vehicle and pedestrian data sets. Experimental results demonstrate that our approach can accurately detect objects under challenging conditions. Note to Practitioners—Object detection is an important part of intelligent vehicle technologies, which play an important role in car sharing services. Object detection provides metadata for collision avoidance, self-driving systems, and driver-assistance systems, which can result in better safety and consumer experiences in car sharing services. Although deep learning has achieved an excellent performance in object detection, they consume a large amount of storage and computing resource, which makes them difficult to be deployed for car sharing services. This paper suggests a novel approach which is based on the generalized Haar filter and the local regression strategy. Our approach is accurate, efficient, and light. The experimental results verify the effectiveness of the proposed approach in car sharing services. [ABSTRACT FROM AUTHOR]

Negative obstacles for field autonomous land vehicles (ALVs) refer to ditches, pits, or terrain with a negative slope, which will bring risks to vehicles in travel. This paper presents a feature fusion based algorithm (FFA) for negative obstacle detection with LiDAR sensors. The main contributions of this paper are fourfold: (1) A novel three-dimensional (3-D) LiDAR setup is presented. With this setup, the blind area around the vehicle is greatly reduced, and the density of LiDAR data is greatly improved, which are critical for ALVs. (2) On the basis of the proposed setup, a mathematical model of the point distribution of a single scan line is deduced, which is used to generate ideal scan lines. (3) With the mathematical model, an adaptive matching filter based algorithm (AMFA) is presented to implement negative obstacle detection. Features of simulated obstacles in each scan line are employed to detect the real negative obstacles. They are supposed to match with features of the potential real obstacles. (4) Grounded on AMFA algorithm, a feature fusion based algorithm is proposed. FFA algorithm fuses all the features generated by different LiDARs or captured at different frames. Bayesian rule is adopted to estimate the weight of each feature. Experimental results show that the performance of the proposed algorithm is robust and stable. Compared with the state-of-the-art techniques, the detection range is improved by 20%, and the computing time is reduced by an order of two magnitudes. The proposed algorithm had been successfully applied on two ALVs, which won the champion and the runner-up in the 'Overcome Danger 2014' ground unmanned vehicle challenge of China. [ABSTRACT FROM AUTHOR]

In research on the navigation and control of an Autonomous Land Vehicle (ALV), the ultrasonic obstacle detection system plays an important role extending the environment cognition capability of the ALV. With a goal of improving the accuracy of ultrasonic obstacle detection, a dynamic data filtering method based on ultrasonic array is presented. The sonar return data is first processed through static filtering according to the geometric relationship of the ultrasonic array. Then, dynamic filtering is executed using the orientation and trajectory information of the vehicle. The dynamic filtering method is compared to the traditional ultrasonic obstacle detection method, which is the static filtering method in a typical field environment. The experiment result demonstrates the validity of the method for solving the fake data problem, and the accuracy of obstacle detection is improved. [ABSTRACT FROM AUTHOR]

We address the issue of visual saliency from three perspectives. First, we consider saliency detection as a frequency domain analysis problem. Second, we achieve this by employing the concept of nonsaliency. Third, we simultaneously consider the detection of salient regions of different size. The paper proposes a new bottom-up paradigm for detecting visual saliency, characterized by a scale-space analysis of the amplitude spectrum of natural images. We show that the convolution of the image amplitude spectrum with a low-pass Gaussian kernel of an appropriate scale is equivalent to an image saliency detector. The saliency map is obtained by reconstructing the 2D signal using the original phase and the amplitude spectrum, filtered at a scale selected by minimizing saliency map entropy. A Hypercomplex Fourier Transform performs the analysis in the frequency domain. Using available databases, we demonstrate experimentally that the proposed model can predict human fixation data. We also introduce a new image database and use it to show that the saliency detector can highlight both small and large salient regions, as well as inhibit repeated distractors in cluttered images. In addition, we show that it is able to predict salient regions on which people focus their attention. [ABSTRACT FROM AUTHOR]

The lane information is essential to the highway intelligent vehicle applications. The direct description of the lanes is lane markings. Many vision methods have been proposed for lane markings detection. But in practice there are some problems to be solved by previous lane tracking systems such as shadows on the road, lighting changes, characters on the road and discontinuous changes in road types. Direction kernel function is proposed for robust detection of the lanes. This method focuses on selecting points on the markings edge by classification. During the classifying, the vanishing point is selected and the parts of the lane marking could form the lanes. The algorithm presented in this paper is proved to be both robust and fast by a large amount of experiments in variable occasions, besides, the algorithm can extract the lanes even in some parts of lane markings missing occasions. [ABSTRACT FROM AUTHOR]

Nowadays, video surveillance has become ubiquitous with the quick development of artificial intelligence. Multi-object detection (MOD) is a key step in video surveillance and has been widely studied for a long time. The majority of existing MOD algorithms follow the "divide and conquer" pipeline and utilize popular machine learning techniques to optimize algorithm parameters. However, this pipeline is usually suboptimal since it decomposes the MOD task into several sub-tasks and does not optimize them jointly. In addition, the frequently used supervised learning methods rely on the labeled data which are scarce and expensive to obtain. Thus, we propose an end-to-end Unsupervised Multi-Object Detection framework for video surveillance, where a neural model learns to detect objects from each video frame by minimizing the image reconstruction error. Moreover, we propose a Memory-Based Recurrent Attention Network to ease detection and training. The proposed model was evaluated on both synthetic and real datasets, exhibiting its potential. [ABSTRACT FROM AUTHOR]

Modelling the multimedia data such as text, images, or videos usually involves the analysis, prediction, or reconstruction of them. The recurrent neural network (RNN) is a powerful machine learning approach to modelling these data in a recursive way. As a variant, the long short-term memory (LSTM) extends the RNN with the ability to remember information for longer. Whilst one can increase the capacity of LSTM by widening or adding layers, additional parameters and runtime are usually required, which could make learning harder. We therefore propose a Tensor LSTM where the hidden states are tensorised as multidimensional arrays (tensors) and updated through a cross-layer convolution. As parameters are spatially shared within the tensor, we can efficiently widen the model without extra parameters by increasing the tensorised size; as deep computations of each time step are absorbed by temporal computations of the time series, we can implicitly deepen the model with little extra runtime by delaying the output. We show by experiments that our model is well-suited for various multimedia data modelling tasks, including text generation, text calculation, image classification, and video prediction. [ABSTRACT FROM AUTHOR]

Vision-based object detection is essential for a multitude of robotic applications. However, it is also a challenging job due to the diversity of the environments in which such applications are required to operate, and the strict constraints that apply to many robot systems in terms of run-time, power and space. To meet these special requirements of robotic applications, we propose an efficient deep network for vision-based object detection. More specifically, for a given image captured by a robot mount camera, we first introduce a novel proposal layer to efficiently generate potential object bounding-boxes. The proposal layer consists of efficient on-line convolutions and effective off-line optimization. Afterwards, we construct a robust detection layer which contains a multiple population genetic algorithm-based convolutional neural network (MPGA-based CNN) module and a TLD-based multi-frame fusion procedure. Unlike most deep learning based approaches, which rely on GPU, all of the on-line processes in our system are able to run efficiently without GPU support. We perform several experiments to validate each component of our proposed object detection approach and compare the approach with some recently published state-of-the-art object detection algorithms on widely used datasets. The experimental results demonstrate that the proposed network exhibits high efficiency and robustness in object detection tasks. [ABSTRACT FROM AUTHOR]