Person re-identification (Re-ID) is an important task in video surveillance which automatically searches and identifies people across different cameras. Despite the extensive Re-ID progress in RGB cameras, few works have studied the Re-ID between infrared and RGB images, which is essentially a cross-modality problem and widely encountered in real-world scenarios. The key challenge lies in two folds, i.e., the lack of discriminative information to re-identify the same person between RGB and infrared modalities, and the difficulty to learn a robust metric towards such a large-scale cross-modality retrieval. In this paper, we tackle the above two challenges by proposing a novel cross-modality generative adversarial network (termed cmGAN). To handle the issue of insufficient discriminative information, we leverage the cutting-edge generative adversarial training to design our own discriminator to learn discriminative feature representation from different modalities. To handle the issue of large-scale cross-modality metric learning, we integrates both identification loss and cross-modality triplet loss, which minimize inter-class ambiguity while maximizing cross-modality similarity among instances. The entire cmGAN can be trained in an end-to-end manner by using standard deep neural network framework. We have quantized the performance of our work in the newly-released SYSU RGB-IR Re-ID benchmark, and have reported superior performance, i.e., Cumulative Match Characteristic curve (CMC) and Mean Average Precision (MAP), over the state-of-the-art works [Wu et al., 2017], respectively.

Accurate and up-to-date mapping and monitoring of rubber plantations is challenging. In this study, we presented a simple method for rapidly and accurately mapping rubber plantations in the Xishuangbanna region of southwest China using phenology-based vegetation index differencing. Temporal profiles of the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Atmospherically Resistant Vegetation Index (ARVI), Normalized Difference Moisture Index (NDMI), and Tasselled Cap Greenness (TCG) for rubber trees, natural forests and croplands were constructed using 11 Landsat 8 OLI images acquired within one year. These vegetation index time series accurately demonstrated the unique seasonal phenological dynamics of rubber trees. Two distinct phenological phases (i.e., defoliation and foliation) of rubber trees were clearly distinguishable from natural forests and croplands. Rubber trees undergo a brief defoliation-foliation process between late December and mid-March. Therefore, vegetation index differencing between the nearly complete defoliation (leaf-off) and full foliation (leaf flushing) phases was used to delineate rubber plantations within fragmented tropical mountainous landscapes. The method presented herein greatly improved rubber plantation classification accuracy. Overall classification accuracies derived from the differences of the five vegetation indices varied from 92% to 96% with corresponding kappa coefficients of 0.84-0.92. These results demonstrate the promising potential of phenology-based vegetation index differencing for mapping and monitoring rubber expansion at the regional scale.

In this paper, we propose a distributed algorithm, called Directed-Distributed Gradient Descent (D-DGD), to solve multi-agent optimization problems over directed graphs. Existing algorithms mostly deal with similar problems under the assumption of undirected networks, i.e., requiring the weight matrices to be doubly-stochastic. The row-stochasticity of the weight matrix guarantees that all agents reach consensus, while the column-stochasticity ensures that each agent's local gradient contributes equally to the global objective. In a directed graph, however, it may not be possible to construct a doubly-stochastic weight matrix in a distributed manner. We overcome this difficulty by augmenting an additional variable for each agent to record the change in the state evolution. In each iteration, the algorithm simultaneously constructs a row-stochastic matrix and a column-stochastic matrix instead of only a doubly-stochastic matrix. The convergence of the new weight matrix, depending on the row-stochastic and column-stochastic matrices, ensures agents to reach both consensus and optimality. The analysis shows that the proposed algorithm converges at a rate of O(, where k is the number of iterations.

No abstract