Siyang Sun

Object detection plays an important role in various visual applications. However, the precision and speed of detector are usually contradictory. One main reason for fast detectors' precision reduction is that small objects are hard to be detected. To address this problem, we propose a multiple receptive field and small-object-focusing weakly-supervised segmentation network (MRFSWSnet) to achieve fast object detection. In MRFSWSnet, multiple receptive fields block (MRF) is used to pay attention to the object and its adjacent background's different spatial location with different weights to enhance the feature's discriminability. In addition, in order to improve the accuracy of small object detection, a small-object-focusing weakly-supervised segmentation module which only focuses on small object instead of all objects is integrated into the detection network for auxiliary training to improve the precision of small object detection. Extensive experiments show the effectiveness of our method on both PASCAL VOC and MS COCO detection datasets. In particular, with a lower resolution version of 300x300, MRFSWSnet achieves 80.9% mAP on VOC2007 test with an inference speed of 15 milliseconds per frame, which is the state-of-the-art detector among real-time detectors.

In this study, a fast object detection algorithm based on binary deep convolution neural networks (CNNs) is proposed. Convolution kernels of different sizes are used to predict classes and bounding boxes of multi‐scale objects directly in the last feature map of a deep CNN. In this way, rapid object detection with acceptable precision loss is achieved. In addition, binary quantisation for weight values and input data of each layer is used to squeeze the networks for faster object detection. Compared to full‐precision convolution, the proposed binary deep CNNs for object detection results in 62 times faster convolutional operations and 32 times memory saving in theory, what's more, the proposed method is easy to be implemented in embedded computing systems because of the binary operation for convolution and low memory requirement. Experimental results on Pascal VOC2007 validate the effectiveness of the authors’ proposed method.

In this paper, a position measurement system, including drogue's landmark detection and position computation for autonomous aerial refueling of unmanned aerial vehicles, is proposed. A multitask parallel deep convolution neural network (MPDCNN) is designed to detect the landmarks of the drogue target. In MPDCNN, two parallel convolution networks are used, and a fusion mechanism is proposed to accomplish the effective fusion of the drogue's two salient parts' landmark detection. Considering the drogue target's geometric constraints, a position measurement method based on monocular vision is proposed. An effective fusion strategy, which fuses the measurement results of drogue's different parts, is proposed to achieve robust position measurement. The error of landmark detection with the proposed method is 3.9%, and it is obviously lower than the errors of other methods. Experimental results on the two KUKA robots platform verify the effectiveness and robustness of the proposed position measurement system for aerial refueling.

In recent years, deep neural networks have achieved great success in the field of computer vision. However, it is still a big challenge to deploy these deep models on resource-constrained embedded devices such as mobile robots, smart phones and so on. Therefore, network compression for such platforms is a reasonable solution to reduce memory consumption and computation complexity. In this paper, a novel channel pruning method based on genetic algorithm is proposed to compress very deep Convolution Neural Networks (CNNs). Firstly, a pre-trained CNN model is pruned layer by layer according to the sensitivity of each layer. After that, the pruned model is fine-tuned based on knowledge distillation framework. These two improvements significantly decrease the model redundancy with less accuracy drop. Channel selection is a combinatorial optimization problem that has exponential solution space. In order to accelerate the selection process, the proposed method formulates it as a search problem, which can be solved efficiently by genetic algorithm. Meanwhile, a two-step approximation fitness function is designed to further improve the efficiency of genetic process. The proposed method has been verified on three benchmark datasets with two popular CNN models: VGGNet and ResNet. On the CIFAR-100 and ImageNet datasets, our approach outperforms several state-of-the-art methods. On the CIFAR-10 and SVHN datasets, the pruned VGGNet achieves better performance than the original model with 8 times parameters compression and 3 times FLOPs reduction.