In this paper, we will investigate the contribution of color names for salient object detection. Each input image is first converted to the color name space, which is consisted of 11 probabilistic channels. By exploring the topological structure relationship between the figure and the ground, we obtain a saliency map through a linear combination of a set of sequential attention maps. To overcome the limitation of only exploiting the surroundedness cue, two global cues with respect to color names are invoked for guiding the computation of another weighted saliency map. Finally, we integrate the two saliency maps into a unified framework to infer the saliency result. In addition, an improved post-processing procedure is introduced to effectively suppress the background while uniformly highlight the salient objects. Experimental results show that the proposed model produces more accurate saliency maps and performs well against 23 saliency models in terms of three evaluation metrics on three public datasets.

The nut weevil (Curculio nucum) is one of the most important and widespread pests in hazelnut orchards. In order to screen entomopathogenic fungal strains with high virulence against C. nucum, the growth rate, sporulation, and cumulative mortality of different Metarhizium anisopliae and Beauveria bassiana strains were investigated, and the process by which M. anisopliae CoM 02 infects C. nucum larvae was observed using scanning electron microscopy. The results indicated that the growth rate and sporulation of different fungal strains significantly differed. Thirteen days after inoculation with M. anisopliae CoM 02, the cumulative mortality of C. nucum larvae reached 100 %, which was considerably higher than that of the other five strains. As the most virulent of the six test strains, the cadaver rate, LT 50 , and LT 90 of M. anisopliae CoM 02 were 93.4 %, 7.05 and 11.90 days, respectively. Analysis of the infection process by scanning electron microscopy showed that the spore attachment, hyphal germination, hyphal rapid growth, and sporulation of M. anisopliae CoM 02 occurred on the 3rd, 5th, 7th, and 11th day after inoculation, respectively, indicating that the infection cycle takes approximately 11 days. This finding suggests that the highly virulent M. anisopliae plays an important role in the biocontrol of C. nucum in China.

Road Detection is a basic task in automated driving field, in which 3D lidar data is commonly used recently. In this paper, we propose to rearrange 3D lidar data into a new organized form to construct direct spatial relationship among point cloud, and put forward new features for real-time road detection tasks. Our model works based on two prerequisites: (1) Road regions are always flatter than non-road regions. (2) Light travels in straight lines in a uniform medium. Based on prerequisite 1, we put forward difference-between-lines feature, while ScanID density and obstacle radial map are generated based on prerequisite 2. According to our method, we construct an array of structures to store and reorganize 3D input firstly. Then, two novel features, difference-between-lines and ScanID density, are extracted, based on which we construct a consistency map and an obstacle map in Bird Eye View (BEV). Finally, the road region is extracted by fusing these two maps and refinement is used to polish up our outcome. We have carried out experiments on the public KITTI-Road benchmark, achieving one of the best performances among the lidar-based road detection methods. To further prove the efficiency of our method on unstructured road, the visual outcomes in rural areas are also proposed.

Multi-object tracking aims to recover the object trajectories, given multiple detections in video frames. Object feature extraction and similarity metric are the two keys to reliably associate trajectories. In this paper, we propose the recurrent metric network (RMNet), a convolutional neural network-recurrent neural network-based similarity metric framework for the multi-object tracking. Given a reference object, the RMNet takes as input random positive and negative detections and outputs similarity scores over time. The RMNet handles the long-term temporal object variations and false object detections by its long-short memory units. With the scores from RMNet, we introduce a batch multiple hypothesis (BMH) strategy, a simple yet efficient data association method for the batch multi-object tracking. BMH generates a hypothesis tree for each object with a dual-threshold hypothesis generation approach and, then, selects the best branch (or hypothesis) for each object as the batch tracking result. Specially, we model the hypothesis selection as a 0-1 programming problem and introduce a reward function to re-find the objects in case of missing detection. We evaluate our RMNet and BMH strategy on several popular datasets: 2DMOT2015, PETS2009, TUD, and KITTI. We achieve a performance comparable or superior to those of the state-of-theart methods.INDEX TERMS Multi-object tracking, pedestrians tracking, recurrent metric networks.

No abstract