The developing of object detection for many purpose has come to various techniques. Some of those works also implement to solve our daily life problem. Those development which are state-of-the-art ...are mostly applicable with many pros than others. In this paper we use one of state-of-the-art of object detection to control a quadcopter i.e. Single Shot MultiBox Detector (SSD). SSD is used to detect an object as quadcopter target for approach mission. SSD also use to keep an eye of the target. The target is represented in shape of ROI location. This ROI or a bounding box location is used as feedback of the control system of quadcopter which will guide the quadcopter to approach. The mission is considered as success if the quadcopter is stopped at minimum range 1 meter toward target. This works shows the successful of object detection implementation by serving IMU responses and measured distance to object responses.
Abstract We present a novel framework aimed at improving video action detection through the integration of heterogeneous features. Conventional action detection methods which focus on modeling the ...relationships between person/object instances rely exclusively on video features and do not exploit valuable intra-instance heterogeneous features, such as person pose, positional information or object category, that can support action recognition. Our proposed framework, termed Heterogeneous Feature Fusion (HFF) framework, addresses this limitation by integrating such intra-instance heterogeneous features for person/object instances, and can improve existing action detection methods. To efficiently exploit each heterogeneous feature, which vary in importance depending on actions and/or scenes, we introduce an attention mechanism to dynamically enhance important heterogeneous features within an instance. Experiments on JHMDB and AVA v2.2 datasets show that our HFF significantly enhances the action detection performance of two existing methods.
Nowadays, object detection has gradually become a quite popular field. From the traditional methods to the methods used at this stage, object detection technology has made great progress, and is ...still continuously developing and innovating. This paper reviews two-stage object detection algorithms used at this stage, explaining in detail the working principles of Faster R-CNN, R-FCN, FPN, and Casecade R-CNN and analyzing the similarities and differences between these four two-stage object detection algorithms. Then we used HSRC2016 ship dataset to perform experiments with Faster R-CNN, R-FCN, FPN, and Casecade R-CNN and compared the effectiveness of them with experimental results.
Abstract
We propose a few-shot object detection algorithm based on sample balance correction, which introduces categorical sample balance correction and positioning sample balance correction on the ...basis of the Faster R-CNN network to improve the performance of few-shot detection, and categorical sample balance correction increases the passing probability of the new type pre-selection box by changing the selection rules of the pre-selection box. And the similarity calculation branch is added to the detection head to help improve the classification ability, and the positioning sample balance correction solves the sample balance in the training process and the balance problem of correcting difficult samples by improving the positioning loss function. Experiments on the PASCAL VOC dataset show that the proposed algorithm improves the detection effect when the sample size is small, up to 3.2 percentage points higher than the comparison algorithm, and has good robustness and generalization ability.
Convolutional Neural Networks (ConvNets) have recently shown promising performance in many computer vision tasks, especially image-based recognition. How to effectively apply ConvNets to ...sequence-based data is still an open problem. This paper proposes an effective yet simple method to represent spatio-temporal information carried in 3D skeleton sequences into three 2D images by encoding the joint trajectories and their dynamics into color distribution in the images, referred to as Joint Trajectory Maps (JTM), and adopts ConvNets to learn the discriminative features for human action recognition. Such an image-based representation enables us to fine-tune existing ConvNets models for the classification of skeleton sequences without training the networks afresh. The three JTMs are generated in three orthogonal planes and provide complimentary information to each other. The final recognition is further improved through multiplicative score fusion of the three JTMs. The proposed method was evaluated on four public benchmark datasets, the large NTU RGB+D Dataset, MSRC-12 Kinect Gesture Dataset (MSRC-12), G3D Dataset and UTD Multimodal Human Action Dataset (UTD-MHAD) and achieved the state-of-the-art results.
Abstract Around-view multi-camera 3D object detection in BEV (Bird’s-Eye-View) space has been a research focus over the past few years. As a typical supervised training task, many researchers promote ...this area with different task-specific key designs, such as exploiting temporal information and correspondence of perspective image plane and BEV space. Most of these works follow the DETR detection framework, yet the nature of learnable queries in DETR, the encodings of objects’ center and bounding box information, have not been discussed in previous studies. In this paper, we take advantage of this prior and further extend it to 3D detection tasks. In 3D object detection, the ground-truth bounding boxes are hardly overlapping. Therefore, the queries should be more diverse under this hypothesis. To achieve this goal, we propose a Plug-in Discrimination Module (PDM) to discriminate learnable queries from all the other queries with a discrimination loss to ensure the diversity of queries. The PDM is a simple train-time-only module. It contains a query projection head to project all the object queries into a common latent space. In the latent space, the discrimination loss is conducted on all the queries. Experimental results show that this design can directly improve the 3D detector’s performance without modifying the detector’s architecture and adding extra inference costs. The NDS improvement on the nuScenes dataset is up to a maximum of 1.62% in the 8th training epoch and remains an average 0.64% improvement in the following epochs, compared with the baseline model.
PDF
