Strengthening collective action to address resource conflict in Lake Kariba, Zambia

Where natural resources are a key component of the rural economy, the ability of the poor to realize their visions for the future depends significantly on institutional structures that govern resource access and management. This case study reports on an initiative on the shores of Lake Kariba in Zambia, where lakeshore residents face competition over fishing, tourism, and commercial aquaculture. Multistakeholder dialogue produced agreements with investors and increased accountability of state agencies and traditional leaders, enabling communities to have greater influence over their futures through improvements in aquatic resource governance. The report documents the rationale for the approach followed and steps in the capacity-building process, discusses obstacles encountered, and identifies lessons for policymakers and practitioners seeking to implement a similar approach.

On the selective action of the cod end meshes of a shrimp trawl

Selectivity studies using cod end and cover to determine the optimum cod end mesh size for commercial size groups of shrimps was carried out at Cochin during 1963-64 fishing season. The normality of the result was checked by trouser cod end method. Although the present investigation was mainly aimed to find out suitable cod end mesh size for commercial varieties of shrimps, five commonly occurring species of fishes were also taken. The 50% escape level, co-efficient of selectivity and selection factor for all the species were worked out. From the findings, the authors stress the necessity of increasing the cod end mesh size from the present condition (25.4 to 31.70 mm) to 41.65 mm fabricated mesh size to avoid depletion of the natural population.

Efficient block segmentation algorithm for true motion estimation

A block-based motion estimation technique is proposed which permits a less general segmentation performed using an efficient deterministic algorithm. Applied to image pairs from the Flower Garden and Table Tennis sequences, the algorithm successfully localizes motion discontinuities and detects uncovered regions. The algorithm is implemented in C on a Sun Sparcstation 20. The gradient-based motion estimation required 28.8 s CPU time, and 500 iterations of the segmentation algorithm required 32.6 s.

Community visioning and action plans: Tonle Sap hub

The process of rolling out the CGIAR Research Program on Aquatic Agricultural Systems (AAS) in 12 target villages in the Tonle Sap region in Cambodia throughout 2013 involved several important tasks at different stages. This report covers one of those tasks: the Community Life Competence Process (CLCP), commonly referred to by stakeholders as "visioning". It has two main objectives: (1) to document the community visioning process, including the development of a community action plan and NGO work plan to monitor progress; and (2) to document village and network profiles of key community stakeholders at the village level.

Segmentation and recognition using structure from motion point clouds

We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3D world structure that vary with object category. We introduce features that project the 3D cues back to the 2D image plane while modeling spatial layout and context. A randomized decision forest combines many such features to achieve a coherent 2D segmentation and recognize the object categories present. Our main contribution is to show how semantic segmentation is possible based solely on motion-derived 3D world structure. Our method works well on sparse, noisy point clouds, and unlike existing approaches, does not need appearance-based descriptors. Experiments were performed on a challenging new video database containing sequences filmed from a moving car in daylight and at dusk. The results confirm that indeed, accurate segmentation and recognition are possible using only motion and 3D world structure. Further, we show that the motion-derived information complements an existing state-of-the-art appearance-based method, improving both qualitative and quantitative performance. © 2008 Springer Berlin Heidelberg.

Semi-supervised video segmentation using tree structured graphical models

We present a novel, implementation friendly and occlusion aware semi-supervised video segmentation algorithm using tree structured graphical models, which delivers pixel labels alongwith their uncertainty estimates. Our motivation to employ supervision is to tackle a task-specific segmentation problem where the semantic objects are pre-defined by the user. The video model we propose for this problem is based on a tree structured approximation of a patch based undirected mixture model, which includes a novel time-series and a soft label Random Forest classifier participating in a feedback mechanism. We demonstrate the efficacy of our model in cutting out foreground objects and multi-class segmentation problems in lengthy and complex road scene sequences. Our results have wide applicability, including harvesting labelled video data for training discriminative models, shape/pose/articulation learning and large scale statistical analysis to develop priors for video segmentation. © 2011 IEEE.